© 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. 149976
    Prev
    Next
    INDEX
    Explanations

    Contests and awards

    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
    åĪ¶
    -0.30
    æ¦Ĥçİĩ
    -0.26
    é»Ķ
    -0.26
    parity
    -0.25
    Gi
    -0.25
    çīĪæĿĥå½Ĵ
    -0.25
    æĬ¥åIJį
    -0.25
    ç®ĹäºĨ
    -0.25
     représ
    -0.24
    fe
    -0.24
    POSITIVE LOGITS
    ascus
    0.28
    AUD
    0.28
     Sweep
    0.26
     Phon
    0.26
    urus
    0.25
     Anthrop
    0.25
     Weinstein
    0.24
    æŁ©
    0.24
     Mond
    0.24
    Intl
    0.24
    Activations Density 0.892%

    No Known Activations