© 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. 56979
    Prev
    Next
    INDEX
    Explanations

    industry

    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
    elic
    -0.28
    ency
    -0.27
    her
    -0.27
    /he
    -0.27
    missible
    -0.26
    å½¢
    -0.26
    失败
    -0.25
    à¹ĥà¸ķ
    -0.25
     her
    -0.25
     failure
    -0.24
    POSITIVE LOGITS
     specifics
    0.26
     wearer
    0.26
    éĨĴæĿ¥
    0.26
    ä¸įçķĻ
    0.25
     traveler
    0.24
    rawid
    0.24
    çļĦ帮åĬ©
    0.24
    ä¸ĵä¸ļçļĦ
    0.23
     himself
    0.23
    å¹´åĨħ
    0.23
    Activations Density 0.238%

    No Known Activations