© 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 EvalsExportsinterp-engineNEWAPI 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. 19-RESID-POST-AA
    11. 7624
    Prev
    Next
    INDEX
    Explanations

    gold and embroidery

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ʏ
    -0.07
    ʊ
    -0.07
    損
    -0.07
    _instances
    -0.07
    的感觉
    -0.06
     CLEAN
    -0.06
     Simple
    -0.06
    學
    -0.06
    ACIÓN
    -0.06
    _orient
    -0.06
    POSITIVE LOGITS
    	pos
    0.08
    .balance
    0.08
    ல
    0.07
    Hunter
    0.07
    传奇
    0.07
    Kal
    0.07
     일반
    0.07
     двигат
    0.07
    iges
    0.06
     vinyl
    0.06
    Activations Density 0.031%

    No Known Activations