© 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. 12-TRANSCODER-HP
    7. 23456
    Prev
    Next
    INDEX
    Explanations

    Technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .aspx
    -0.29
     thú
    -0.29
    éĻIJ
    -0.29
    _third
    -0.28
    _rq
    -0.26
    даÑĩи
    -0.26
    uddy
    -0.25
     gÅĤów
    -0.25
    解åĨ³æĸ¹æ¡Ī
    -0.25
    imeter
    -0.25
    POSITIVE LOGITS
     varies
    0.27
    lesi
    0.26
    vary
    0.26
    产çĶŁäºĨ
    0.26
     Ital
    0.26
     intervened
    0.25
     natur
    0.25
    EMU
    0.25
    ä¸įéĶĪ
    0.25
    Recorder
    0.24
    Activations Density 0.000%

    No Known Activations