© 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. 31-TRANSCODER-HP
    7. 19966
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æĽ¿
    -0.30
     dare
    -0.28
    awe
    -0.28
    æĬĽ
    -0.28
    irl
    -0.28
    eced
    -0.27
    éĢĤå½ĵ
    -0.27
    ({_
    -0.27
    alley
    -0.26
     Ital
    -0.26
    POSITIVE LOGITS
    enguin
    0.29
     tact
    0.27
    _probe
    0.27
    è¶ĬãģĹ
    0.26
    鹧
    0.26
    udit
    0.25
     trib
    0.25
    utt
    0.25
     depend
    0.25
     depends
    0.25
    Activations Density 0.104%

    No Known Activations