© 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. 8102
    Prev
    Next
    INDEX
    Explanations

    programming questions and answers

    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
    Not in Any Lists

    No Comments

    Negative Logits
    èĬ¦
    -0.28
    licher
    -0.26
    ä¸Ń
    -0.26
     rais
    -0.25
    çļĦ表çİ°
    -0.25
    å½¢
    -0.24
     vra
    -0.24
    æ´»
    -0.23
    ya
    -0.23
    лÑı
    -0.23
    POSITIVE LOGITS
    arth
    0.26
    intérieur
    0.26
    arine
    0.26
    ÂĢÂĻ
    0.26
    åħ±åIJĮåĬªåĬĽ
    0.25
    touches
    0.25
    avern
    0.25
    å°º
    0.25
    èĦĨå¼±
    0.24
    樽
    0.24
    Activations Density 0.004%

    No Known Activations