© 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. 149660
    Prev
    Next
    INDEX
    Explanations

    API code

    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
    ÑĪей
    -0.28
    umat
    -0.27
    çݯçIJĥ
    -0.26
    umbo
    -0.26
    nier
    -0.26
    oton
    -0.25
    iosa
    -0.24
    agine
    -0.24
    loth
    -0.24
    EGA
    -0.24
    POSITIVE LOGITS
     und
    0.26
     lÃłnh
    0.25
    _der
    0.25
    kim
    0.24
    Commit
    0.24
    æĺŁ
    0.23
    CTS
    0.23
    çīĩåĪ»
    0.23
    und
    0.23
     cuid
    0.23
    Activations Density 0.120%

    No Known Activations