© 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. 9205
    Prev
    Next
    INDEX
    Explanations

    code-related tokens

    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
    åİ»ä¸ĸ
    -0.30
     murder
    -0.29
    éĢĿä¸ĸ
    -0.28
    judge
    -0.28
    æŃ»äºĨ
    -0.28
     death
    -0.28
    åįĸæİī
    -0.28
    æĿĢ害
    -0.28
     dies
    -0.27
     judge
    -0.27
    POSITIVE LOGITS
    å°Ĭ
    0.30
    elines
    0.28
     <<=
    0.27
    å¾ħ
    0.25
    ELS
    0.25
    elm
    0.25
    '],['
    0.24
    é¦ĸ饰
    0.24
    ').'
    0.24
    /vendor
    0.24
    Activations Density 0.001%

    No Known Activations