© 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. 57195
    Prev
    Next
    INDEX
    Explanations

    Code and documentation

    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
    è¿Ļåı¥è¯Ŀ
    -0.39
    è¯Ĺåı¥
    -0.38
    ä¸Ģåı¥
    -0.38
    åı¥
    -0.37
     phrases
    -0.34
    åı¥åŃIJ
    -0.34
     sentence
    -0.34
    åĩłåı¥
    -0.33
    åı¥è¯Ŀ
    -0.32
     sentences
    -0.31
    POSITIVE LOGITS
     fileList
    0.31
     documentaries
    0.31
    ossier
    0.31
     Assembly
    0.30
     Wizard
    0.29
     assembly
    0.29
    assembly
    0.28
     files
    0.28
     notebooks
    0.28
     simul
    0.27
    Activations Density 0.000%

    No Known Activations