© 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. 23617
    Prev
    Next
    INDEX
    Explanations

    adaptive

    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
    åĹª
    -0.29
     contr
    -0.27
    ********************************************************************************
    -0.26
    主é¢ĺ
    -0.26
    CR
    -0.26
    象å¾ģ
    -0.26
    _skb
    -0.26
     unt
    -0.25
    wc
    -0.25
    æĪijçŁ¥éģĵ
    -0.25
    POSITIVE LOGITS
    ä¸Ģæī¹
    0.27
    ãĤ¸ãĥ£ãĥ¼
    0.26
     Spiral
    0.26
    ennie
    0.25
    åĩłåĪĨ
    0.25
    оÑĩнÑĭе
    0.25
    personal
    0.25
    angan
    0.24
    alse
    0.24
    大æī¹
    0.23
    Activations Density 0.002%

    No Known Activations