© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 83799
    Prev
    Next
    INDEX
    Explanations

    software libraries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Alleg
    -0.08
     Full
    -0.08
    lege
    -0.08
     publicKey
    -0.08
    ulerAngles
    -0.08
     laut
    -0.07
     lands
    -0.07
    gly
    -0.07
    图书
    -0.07
     взгляд
    -0.07
    POSITIVE LOGITS
     wir
    0.07
    //--------------------------------------------------------------------------------
    0.07
     motivations
    0.07
    _SITE
    0.07
    Raises
    0.07
     zobowiąz
    0.07
    สถ
    0.07
     fantastic
    0.07
    	update
    0.07
    ча
    0.07
    Activations Density 0.056%

    No Known Activations