© 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. 23-TRANSCODER-HP
    7. 25064
    Prev
    Next
    INDEX
    Explanations

    directions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pros
    -0.28
    iku
    -0.26
     form
    -0.25
    rh
    -0.25
    upa
    -0.25
    unami
    -0.24
    .nodeType
    -0.24
     dil
    -0.24
     rh
    -0.24
     kind
    -0.23
    POSITIVE LOGITS
    orary
    0.33
    æľīæĿ¡ä»¶çļĦ
    0.30
    滢
    0.27
    ledge
    0.27
    quier
    0.26
    nowled
    0.26
    erness
    0.26
    rary
    0.25
    nowledge
    0.24
    :auto
    0.24
    Activations Density 0.021%

    No Known Activations