© 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. 24-TRANSCODER-HP
    7. 150201
    Prev
    Next
    INDEX
    Explanations

    encyclopedia article snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sst
    -0.26
     dash
    -0.25
    .Fields
    -0.24
    #.
    -0.24
     synchronize
    -0.23
     draining
    -0.23
     align
    -0.23
    ÑģÑĤвоваÑĤÑĮ
    -0.23
    Reviewer
    -0.23
    Dash
    -0.23
    POSITIVE LOGITS
    æĬľãģij
    0.27
    WW
    0.26
    çļĦçľ¼åħī
    0.26
    èµĦæĸĻ
    0.25
    //--
    0.24
     Poll
    0.24
    FileManager
    0.24
    第ä¸ī代
    0.23
     Dirk
    0.23
    åıĹä¸įäºĨ
    0.22
    Activations Density 0.898%

    No Known Activations