© 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. 108290
    Prev
    Next
    INDEX
    Explanations

    to or with

    np_max-act-logits · gemini-2.0-flash
    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
    çŃīå¾ħ
    -0.38
     waiting
    -0.35
    Waiting
    -0.30
    çŃīåĢĻ
    -0.30
    åĹ²
    -0.30
     awaiting
    -0.30
     Waiting
    -0.29
    Await
    -0.29
     waits
    -0.29
    _waiting
    -0.29
    POSITIVE LOGITS
    ilio
    0.29
    éĴ³
    0.28
    styles
    0.25
     mixin
    0.25
    Mix
    0.24
    马æĭīæĿ¾
    0.24
    _mix
    0.24
     xuyên
    0.23
    isateur
    0.23
     Mercer
    0.23
    Activations Density 0.979%

    No Known Activations