© 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. 23-TRANSCODER-HP
    7. 24983
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     poo
    -0.28
    idis
    -0.26
    ä¹Łæĺ¯ä¸Ģ个
    -0.24
    åľ¨ç½ij绾
    -0.24
     Magical
    -0.24
    åĪĽæĸ°èĥ½åĬĽ
    -0.24
    æ¶Īæģ¯ç§°
    -0.24
     pillar
    -0.24
     Unused
    -0.23
    æµĩæ°´
    -0.23
    POSITIVE LOGITS
    eval
    0.27
    oney
    0.27
    ój
    0.27
    regon
    0.26
    _coordinates
    0.26
     God
    0.26
    yp
    0.26
     closed
    0.26
    _CN
    0.25
    ç¥ŀ
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.