© 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. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 53704
    Prev
    Next
    INDEX
    Explanations

    Asking questions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åŁİåİ¿
    -0.27
    è¾ĵéĢģ
    -0.26
    两家
    -0.26
    herits
    -0.25
     Doyle
    -0.25
    PACE
    -0.25
    movies
    -0.25
    æĸ°ä¸ĸ纪
    -0.25
     downt
    -0.25
    èµĽ
    -0.24
    POSITIVE LOGITS
    éĹ®
    0.48
     ask
    0.44
    åķı
    0.41
     asking
    0.37
     items
    0.36
    ask
    0.36
     asked
    0.36
    è¿ĻäºĽéĹ®é¢ĺ
    0.36
     questions
    0.35
     asks
    0.31
    Activations Density 0.014%

    No Known Activations