© 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. 23645
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    å¾Ĥ
    -0.37
    hua
    -0.27
     :+:
    -0.26
    太éĺ³åŁİ
    -0.25
    åł
    -0.24
    æł²
    -0.24
     exposure
    -0.24
    åĪijäºĭæ¡Ī件
    -0.24
     getResource
    -0.24
    alom
    -0.23
    POSITIVE LOGITS
    {$
    0.29
    éªĪ
    0.27
    lop
    0.26
    ç¼´
    0.26
    finger
    0.25
    éľĩ
    0.25
    afi
    0.25
    æĮ¯
    0.24
    æĶ¶
    0.24
    :animated
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.