© 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. 108074
    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
    FromBody
    -0.36
    lec
    -0.30
    èĥŃ
    -0.25
    Violation
    -0.25
    .deserialize
    -0.25
    çĤ¹å¤´
    -0.25
    æĶ¿çŃĸ
    -0.24
    (HttpStatusCode
    -0.24
    çļĦåĬ¨åĬĽ
    -0.24
    evice
    -0.24
    POSITIVE LOGITS
     Pent
    0.29
    åĪļ
    0.28
    æĺİæĺŁ
    0.25
    çĶ·åŃ©
    0.25
    IDADE
    0.24
    .rs
    0.23
    колÑĮ
    0.23
     subs
    0.23
    建设
    0.23
    jected
    0.23
    Activations Density 0.022%

    No Known Activations

    This feature has no known activations.