© 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. 8433
    Prev
    Next
    INDEX
    Explanations

    PHP code

    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
    ="{{
    -0.07
     blog
    -0.07
     Determines
    -0.07
    EDGE
    -0.07
    \Tests
    -0.07
    ⏌
    -0.06
     %@",
    -0.06
     cres
    -0.06
     DateTimeKind
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     Stern
    0.08
     부
    0.07
     banc
    0.07
     abusing
    0.06
     Lis
    0.06
    arden
    0.06
     Walker
    0.06
    	dispatch
    0.06
    -dialog
    0.06
    Port
    0.06
    Activations Density 0.053%

    No Known Activations