© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RESID-POST-AA
    11. 65565
    Prev
    Next
    INDEX
    Explanations

    inflater

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .quality
    -0.07
    sendMessage
    -0.07
     jm
    -0.07
    =datetime
    -0.07
    seat
    -0.07
    byte
    -0.07
    _upgrade
    -0.07
    אוטומ
    -0.07
    skip
    -0.07
     SETTINGS
    -0.06
    POSITIVE LOGITS
    _barang
    0.07
     assembled
    0.07
     Bain
    0.07
    raf
    0.07
     transform
    0.07
    ificado
    0.07
     tenga
    0.07
     Dani
    0.06
     것입니다
    0.06
     реакци
    0.06
    Activations Density 0.000%

    No Known Activations