© 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. 58135
    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
     emb
    -0.31
    аÑĢи
    -0.28
     measures
    -0.27
     creatures
    -0.25
    ãĤ¹ãĤ¿ãĥĥãĥķ
    -0.24
     qualities
    -0.24
    大éĿ¢ç§¯
    -0.24
    lov
    -0.23
     Measures
    -0.23
    åIJĪ
    -0.23
    POSITIVE LOGITS
    ofile
    0.33
    ieve
    0.26
    ".↵↵↵↵
    0.25
    ophage
    0.24
     sharing
    0.24
    ankan
    0.24
    æŃ»äºĨ
    0.24
    æľįåĬ¡ä½ĵç³»
    0.24
    ä½Ĩè¿Ļ
    0.23
    anford
    0.23
    Activations Density 0.001%

    No Known Activations