© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 22245
    Prev
    Next
    INDEX
    Explanations

    Stock market tickers

    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
    witter
    -0.07
    '/>↵
    -0.07
    꽃
    -0.07
     Ole
    -0.07
     MET
    -0.07
    公交
    -0.06
    務
    -0.06
     tüket
    -0.06
     '),
    -0.06
    DET
    -0.06
    POSITIVE LOGITS
    Downloading
    0.07
    .serializer
    0.07
    .matcher
    0.07
     swear
    0.07
    Bei
    0.07
     FAQ
    0.07
    -packages
    0.07
     VGA
    0.07
    Upgrade
    0.06
    (any
    0.06
    Activations Density 0.052%

    No Known Activations