© 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. 14-TRANSCODER-HP
    7. 41434
    Prev
    Next
    INDEX
    Explanations

    statistical risk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _FT
    -0.26
    nces
    -0.25
    .Promise
    -0.25
    ineTransform
    -0.25
    AMENT
    -0.24
     воÑģ
    -0.24
    xCE
    -0.24
    éķ«
    -0.24
    ÑĤоÑĢ
    -0.23
    inka
    -0.23
    POSITIVE LOGITS
    æ±
    0.28
    èµĽ
    0.27
    åįĸåĩº
    0.27
    å¡ŀ
    0.27
    çħ
    0.26
     excluded
    0.26
    GN
    0.26
    Logged
    0.24
    quee
    0.24
    =batch
    0.24
    Activations Density 0.175%

    No Known Activations