© 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. 149657
    Prev
    Next
    INDEX
    Explanations

    ert

    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
    iances
    -0.31
     human
    -0.26
    esis
    -0.25
    RelativeTo
    -0.24
    æĢ§ä»·æ¯Ķ
    -0.24
    ä¹Ŀå·ŀ
    -0.24
    家éŨåı£
    -0.24
     expans
    -0.23
     diffuse
    -0.23
    åĨ°éĽª
    -0.23
    POSITIVE LOGITS
    ccount
    0.27
    ettes
    0.26
    çŁ¿çī©
    0.25
    çŁ³åĮĸ
    0.25
    涨
    0.25
    ény
    0.24
    roys
    0.24
    å¾·æĭī
    0.24
     fres
    0.24
    CRE
    0.24
    Activations Density 0.109%

    No Known Activations