© 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. 8771
    Prev
    Next
    INDEX
    Explanations

    page

    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
     dol
    -0.26
    ugo
    -0.26
    ä¸ĢæµģçļĦ
    -0.25
    LAY
    -0.25
    .Full
    -0.25
    pto
    -0.24
     Bell
    -0.24
     sidel
    -0.24
    udy
    -0.24
    æľĢ好æĺ¯
    -0.23
    POSITIVE LOGITS
    sworth
    0.28
    -ab
    0.27
    ughter
    0.26
    è±ģ
    0.26
    æĬĺ
    0.25
    æī©å¼ł
    0.25
     Blond
    0.24
     Martial
    0.24
    .cls
    0.24
    缺失
    0.24
    Activations Density 0.114%

    No Known Activations