© 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. 8949
    Prev
    Next
    INDEX
    Explanations

    math expressions

    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
    atég
    -0.28
    ä¸Ĭæĸ¹
    -0.28
    èĬ¥
    -0.27
     perm
    -0.26
     nich
    -0.26
    ä¸ĭæĸ¹
    -0.25
    æľ¬é¢Ĩ
    -0.25
    許
    -0.24
    -arm
    -0.24
    èİĵ
    -0.24
    POSITIVE LOGITS
    //=
    0.28
     resultant
    0.26
     resil
    0.26
    shake
    0.26
     trait
    0.26
    :i
    0.25
    çĸĸ
    0.25
    产åĵģè´¨éĩı
    0.24
    trait
    0.24
    åĿļå®ļ
    0.23
    Activations Density 0.022%

    No Known Activations