© 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. 70975
    Prev
    Next
    INDEX
    Explanations

    wake

    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
    subs
    -0.07
     Deck
    -0.07
    大赛
    -0.06
    )f
    -0.06
    拓宽
    -0.06
    Each
    -0.06
    loth
    -0.06
     shaped
    -0.06
    报道
    -0.06
     đậm
    -0.06
    POSITIVE LOGITS
     düzey
    0.07
     salle
    0.07
    	want
    0.07
    	RE
    0.07
     kotlinx
    0.07
     IsPlainOldData
    0.07
    ゐ
    0.07
     framebuffer
    0.07
     更
    0.07
     Initi
    0.07
    Activations Density 0.004%

    No Known Activations