© 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. 8572
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    åį´æĺ¯
    -0.27
    ä¸įè¿ĩ
    -0.27
    schemas
    -0.25
    çĦ¶èĢĮ
    -0.25
    说çļĦæĺ¯
    -0.25
    çĬ¬
    -0.24
     However
    -0.24
    侧
    -0.24
    (sid
    -0.23
    However
    -0.23
    POSITIVE LOGITS
    ï¼Į“
    0.38
    ï¼ĮãĢĬ
    0.29
    ï¼Į↵↵
    0.28
    ï¼Įåľ¨
    0.28
    ï¼Į↵
    0.28
    &e
    0.27
    ï¼Į
    0.27
    ØĮ
    0.25
    ®,
    0.25
    (),č↵
    0.25
    Activations Density 0.010%

    No Known Activations