© 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. 19-RESID-POST-AA
    11. 7399
    Prev
    Next
    INDEX
    Explanations

    home (baseball)

    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
    	tv
    -0.07
    Pdf
    -0.07
     identification
    -0.07
     KK
    -0.07
     childbirth
    -0.06
     Mueller
    -0.06
     обеспеч
    -0.06
     Obtain
    -0.06
     ل
    -0.06
     vans
    -0.06
    POSITIVE LOGITS
    _secs
    0.08
     repos
    0.07
    Effects
    0.07
    .IDENTITY
    0.07
    :image
    0.07
    ucson
    0.07
     versatile
    0.07
    ajs
    0.07
    过于
    0.07
    ザ
    0.07
    Activations Density 0.006%

    No Known Activations