© 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. 27-TRANSCODER-HP
    7. 58481
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    izedName
    -0.30
    qid
    -0.28
    黥
    -0.27
     fret
    -0.25
    ót
    -0.25
    portrait
    -0.25
    ä»Ģä¹Īäºĭæĥħ
    -0.24
     quartz
    -0.24
    _FORE
    -0.24
    大å¦Ī
    -0.24
    POSITIVE LOGITS
     Albania
    0.33
    ules
    0.30
    ething
    0.28
    çī©
    0.27
    ulner
    0.27
    ombo
    0.27
    ulnerable
    0.25
    åĵij
    0.25
    ({_
    0.25
     peanuts
    0.24
    Activations Density 0.000%

    No Known Activations