© 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. 11-RESID-POST-AA
    11. 67408
    Prev
    Next
    INDEX
    Explanations

    Licensing

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Battery
    -0.10
    忐
    -0.08
    =R
    -0.08
    醢
    -0.07
    ？↵
    -0.07
     Tell
    -0.07
    Containers
    -0.07
    甚至还
    -0.07
     reserved
    -0.06
     וזה
    -0.06
    POSITIVE LOGITS
    produk
    0.08
     clubhouse
    0.07
     income
    0.07
    ulate
    0.07
    	where
    0.07
    слож
    0.07
     полностью
    0.06
    (!_
    0.06
    ой
    0.06
    pole
    0.06
    Activations Density 0.002%

    No Known Activations