© 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. 25-TRANSCODER-HP
    7. 108775
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĪĨåĮĸ
    -0.28
    '],'
    -0.26
    ']+
    -0.26
     Rol
    -0.25
    åIJĥè¿ĩ
    -0.25
     fragmentation
    -0.24
     combined
    -0.24
     Responsibility
    -0.23
    rug
    -0.23
     converged
    -0.23
    POSITIVE LOGITS
    offs
    0.30
    Off
    0.30
    aging
    0.28
     Off
    0.27
    icol
    0.27
    èĢģ大
    0.27
    éļĶ
    0.26
    æµİåįĹå¸Ĥ
    0.26
    itra
    0.26
    agem
    0.26
    Activations Density 0.229%

    No Known Activations

    This feature has no known activations.