© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5115
    Prev
    Next
    INDEX
    Explanations

    possibility, intention, future

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    äºĨèĩªå·±çļĦ
    -0.27
     replacements
    -0.27
    äºĨä»ĸçļĦ
    -0.25
     taskId
    -0.25
    SOR
    -0.25
    egas
    -0.24
     consumes
    -0.24
    ruk
    -0.24
    ques
    -0.23
    éĽĢ
    -0.23
    POSITIVE LOGITS
     hitch
    0.27
    .slice
    0.27
    _expect
    0.24
    ogne
    0.24
    NDER
    0.24
     besten
    0.24
    agon
    0.24
    olland
    0.24
    nice
    0.23
     conten
    0.23
    Activations Density 0.873%

    No Known Activations