© 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. 70693
    Prev
    Next
    INDEX
    Explanations

    =

    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
     dred
    -0.08
     meme
    -0.07
    ع
    -0.06
    무
    -0.06
     lien
    -0.06
     nex
    -0.06
     DHS
    -0.06
     тех
    -0.06
     jong
    -0.06
     dang
    -0.06
    POSITIVE LOGITS
    셒
    0.07
    Certificate
    0.07
    substring
    0.07
    }):
    0.07
     publications
    0.07
    ibold
    0.07
    �
    0.07
    Silver
    0.06
    各行各
    0.06
    ⨍
    0.06
    Activations Density 0.005%

    No Known Activations