© 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. 53224
    Prev
    Next
    INDEX
    Explanations

    Javascript

    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
    aggi
    -0.30
    å°¾
    -0.29
    æŀŀ
    -0.27
    tails
    -0.26
    éĩį
    -0.26
    tail
    -0.26
    ç¨Ģ
    -0.26
     Riding
    -0.26
    èĥ¡
    -0.25
    ela
    -0.25
    POSITIVE LOGITS
    _exc
    0.24
     Avalanche
    0.24
    ä¸į失
    0.24
    ãģĵãģ¨ãģĮãģ§ãģįãģ¾ãģĻ
    0.24
    _Exception
    0.24
    ãģĵãģ¨ãģ«
    0.23
    Massage
    0.23
     metab
    0.23
     st
    0.23
    éĻĩ
    0.23
    Activations Density 0.009%

    No Known Activations