© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 57405
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
     Strand
    -0.28
     Bennett
    -0.26
     Marks
    -0.25
    endpoint
    -0.25
    衽
    -0.25
     Tie
    -0.25
    åįļ彩
    -0.25
    endor
    -0.24
     вÑģÑĤÑĢеÑĩ
    -0.24
    .endpoint
    -0.24
    POSITIVE LOGITS
    mer
    0.37
    utzer
    0.30
    ç«ĭ
    0.29
    ur
    0.28
    idos
    0.26
    res
    0.26
    åķĨ
    0.25
    agher
    0.25
    amburg
    0.25
    yyy
    0.25
    Activations Density 0.011%

    No Known Activations

    This feature has no known activations.