© 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. 7717
    Prev
    Next
    INDEX
    Explanations

    mammals

    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
    rarian
    -0.29
    ricular
    -0.29
    puty
    -0.28
    aber
    -0.26
    è¿İ
    -0.26
    idores
    -0.24
    developers
    -0.24
    éĻį
    -0.24
     Heads
    -0.23
    ereal
    -0.23
    POSITIVE LOGITS
    ÅŁim
    0.30
    æĴĩ
    0.27
    .strategy
    0.27
    .Suppress
    0.26
    ppv
    0.25
    ÑģÑĤÑĢоиÑĤелÑĮ
    0.25
    UME
    0.25
    æĢĿæĥ³æĶ¿æ²»
    0.25
    建设工ç¨ĭ
    0.24
    ufs
    0.24
    Activations Density 0.054%

    No Known Activations