© 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. 9372
    Prev
    Next
    INDEX
    Explanations

    Get

    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
    åĨ
    -0.28
    nown
    -0.26
    orget
    -0.25
     requestOptions
    -0.24
    ocado
    -0.24
    europ
    -0.24
    åĢĴ
    -0.24
    è§īéĨĴ
    -0.24
    æĬķèµĦé¢Ŀ
    -0.24
    æĵ¤
    -0.24
    POSITIVE LOGITS
    ableObject
    0.31
    _Handler
    0.25
    idan
    0.25
    ÑģÑĤÑĮ
    0.25
    babel
    0.25
    æľīæĿ¡ä»¶
    0.25
    vos
    0.24
     dynamic
    0.24
     fines
    0.24
    ilibrium
    0.24
    Activations Density 0.003%

    No Known Activations