© 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. 16992
    Prev
    Next
    INDEX
    Explanations

    transform

    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
     operate
    -0.07
     вели
    -0.07
     vast
    -0.07
     volumes
    -0.07
    枇
    -0.07
     geological
    -0.07
    .extract
    -0.07
     trí
    -0.07
    -mile
    -0.07
     incorporate
    -0.07
    POSITIVE LOGITS
    城县
    0.07
    쌰
    0.07
    FirstResponder
    0.07
    izacion
    0.07
     naprawdę
    0.07
    👏
    0.07
     catégorie
    0.07
    城
    0.07
    ção
    0.06
     '">
    0.06
    Activations Density 0.003%

    No Known Activations