© 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. 23143
    Prev
    Next
    INDEX
    Explanations

    gymn

    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
    对åŃ©åŃIJ
    -0.40
    家éķ¿
    -0.40
     parents
    -0.38
     Parents
    -0.35
     parent
    -0.34
    家éķ¿ä»¬
    -0.34
     Parent
    -0.33
    parents
    -0.32
    家éķ·
    -0.32
    Parents
    -0.32
    POSITIVE LOGITS
    诱æĥij
    0.29
    heads
    0.26
    illin
    0.26
    èĪ«
    0.25
    ods
    0.24
    ä¾¦æŁ¥
    0.24
    èīĩ
    0.24
    æ§Ĭ
    0.24
     shm
    0.23
     Div
    0.23
    Activations Density 0.000%

    No Known Activations