© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 106969
    Prev
    Next
    INDEX
    Explanations

    research papers

    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
    Negative Logits
    /respond
    -0.29
     medium
    -0.27
    rets
    -0.26
    欺è¯Ī
    -0.26
    ãģĸ
    -0.25
    medium
    -0.24
     Paradise
    -0.24
     studs
    -0.23
    uche
    -0.23
    validated
    -0.23
    POSITIVE LOGITS
    åĸī
    0.26
    basis
    0.26
    FFFFFF
    0.26
    DIST
    0.24
    oen
    0.24
    çī¹æ®ĬæĥħåĨµ
    0.24
    atsu
    0.24
    arias
    0.23
     mcc
    0.23
    blink
    0.23
    Activations Density 0.046%

    No Known Activations