© 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. 149929
    Prev
    Next
    INDEX
    Explanations

    technical/code 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
     tard
    -0.28
    -BEGIN
    -0.25
    ARSE
    -0.25
    estr
    -0.25
    .hibernate
    -0.25
    hone
    -0.25
    .getDate
    -0.24
    éĽĨåIJĪ
    -0.24
    refixer
    -0.24
    常常
    -0.24
    POSITIVE LOGITS
    模æĭŁ
    0.29
    peror
    0.29
    imals
    0.28
    Loaded
    0.28
    æİ·
    0.28
     Loaded
    0.27
    ittest
    0.26
    å¬ī
    0.25
     spray
    0.25
    .loaded
    0.25
    Activations Density 1.069%

    No Known Activations