© 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. 107375
    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
     Growth
    -0.32
     growth
    -0.28
    growth
    -0.28
    ucky
    -0.27
    hope
    -0.25
    ophe
    -0.25
    nze
    -0.25
     Controls
    -0.25
    COR
    -0.25
     Next
    -0.25
    POSITIVE LOGITS
     pans
    0.27
    ,'%
    0.26
     household
    0.26
    imators
    0.26
    iors
    0.25
    fits
    0.24
    iphers
    0.24
    /rs
    0.24
     aperture
    0.24
    imating
    0.24
    Activations Density 0.034%

    No Known Activations

    This feature has no known activations.