© 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. 107086
    Prev
    Next
    INDEX
    Explanations

    phone calls

    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
     disadvantage
    -0.25
    arma
    -0.24
     heels
    -0.24
    åŀ¤
    -0.24
    è°£è¨Ģ
    -0.24
    -separated
    -0.24
    printStats
    -0.24
    帽
    -0.23
    è´¿
    -0.23
    éķĽ
    -0.23
    POSITIVE LOGITS
    .Serve
    0.28
    obia
    0.27
    cene
    0.27
    Appe
    0.26
    ModelError
    0.26
    Serve
    0.25
    èĪIJ
    0.25
     constit
    0.25
    serve
    0.25
    uming
    0.24
    Activations Density 0.894%

    No Known Activations