© 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. 15-RESID-POST-AA
    11. 82237
    Prev
    Next
    INDEX
    Explanations

    abhorrent

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Apr
    -0.07
     Well
    -0.06
     disclaimer
    -0.06
    。，
    -0.06
    阔
    -0.06
     sooner
    -0.06
    pherd
    -0.06
    かなり
    -0.06
     decade
    -0.06
     AGRE
    -0.06
    POSITIVE LOGITS
    _RANDOM
    0.07
    =__
    0.07
    	Class
    0.07
    .Field
    0.07
     الإنس
    0.07
    _robot
    0.07
    =@"
    0.07
    _fast
    0.07
    大米
    0.07
    .top
    0.07
    Activations Density 0.046%

    No Known Activations