© 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. 18-TRANSCODER-HP
    7. 89436
    Prev
    Next
    INDEX
    Explanations

    mainly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åħ¨æł¡
    -0.30
    ä¸įåIJĮç±»åŀĭ
    -0.28
    uga
    -0.28
     rowNum
    -0.27
    ä¹Łç®Ĺ
    -0.25
    _Tick
    -0.25
    #pragma
    -0.24
    IRA
    -0.24
    _conditions
    -0.24
     ФедеÑĢаÑĨии
    -0.24
    POSITIVE LOGITS
    æīij
    0.28
    ä¸ĢçĤ¹
    0.28
    éģŀ
    0.27
    åħĪè¿Ľ
    0.26
    交ä»ĺ
    0.26
    æĿ¾
    0.26
     Advanced
    0.26
    é»Ħ
    0.25
    ianne
    0.25
    ä¸ĢæŃ¥
    0.25
    Activations Density 17.825%

    No Known Activations