© 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. 57660
    Prev
    Next
    INDEX
    Explanations

    Code and technical language

    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
    ï¼īč↵
    -0.23
    社
    -0.22
    Âł
    -0.22
    ³³³
    -0.22
    çĪ¶äº²
    -0.21
    å¹¹
    -0.21
    ³³³³³³³
    -0.21
    ned
    -0.21
     propagated
    -0.21
    å·´å·´
    -0.21
    POSITIVE LOGITS
    itemName
    0.23
    fieldset
    0.23
     Deborah
    0.22
    çļĦæĸĩåŃĹ
    0.22
     lak
    0.22
     sty
    0.21
     Plaint
    0.21
    Unavailable
    0.20
     Plaintiff
    0.20
    ovsky
    0.20
    Activations Density 0.007%

    No Known Activations