© 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. 108247
    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
    ÑĩеÑģÑĤво
    -0.27
    å¶Ĥ
    -0.26
    uhan
    -0.25
    wise
    -0.25
    èIJ¥
    -0.25
    baz
    -0.25
     rib
    -0.25
    inine
    -0.25
     baz
    -0.24
     Troll
    -0.24
    POSITIVE LOGITS
    é¢ł
    0.28
    creat
    0.26
    rov
    0.25
    ä¼½
    0.25
    å±ĢéĻIJ
    0.24
    comings
    0.23
     LY
    0.23
    endtime
    0.23
    eren
    0.23
     Thy
    0.23
    Activations Density 0.010%

    No Known Activations

    This feature has no known activations.