© 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. 8487
    Prev
    Next
    INDEX
    Explanations

    system, code, open source

    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
     washing
    -0.30
     prive
    -0.29
     radios
    -0.28
    æ´Ĺ
    -0.27
     wash
    -0.26
    ıkl
    -0.26
     kettle
    -0.25
    è¿ĺåİŁ
    -0.25
    ,true
    -0.25
    æĿ¯åŃIJ
    -0.24
    POSITIVE LOGITS
     Tie
    0.28
    ç³»ç»Ł
    0.28
    éĤ£äºº
    0.27
    locs
    0.27
     æĽ
    0.26
     Specs
    0.26
     System
    0.24
     tie
    0.24
    æľīçļĦ人
    0.24
     Systems
    0.24
    Activations Density 0.011%

    No Known Activations