© 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. 30-TRANSCODER-HP
    7. 96365
    Prev
    Next
    INDEX
    Explanations

    chromium

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æķ£
    -0.37
    fare
    -0.28
     scatter
    -0.26
    ủ
    -0.26
    uds
    -0.26
     deluxe
    -0.26
     Scatter
    -0.26
    orld
    -0.26
    æĦŁ
    -0.25
     Disp
    -0.25
    POSITIVE LOGITS
    rome
    0.29
    etect
    0.29
    ungs
    0.28
    éĵ¤
    0.28
    nis
    0.27
    Violation
    0.27
    롬
    0.27
    ä¸ĢæĹ¥
    0.26
     íķ¨
    0.25
     Bij
    0.24
    Activations Density 0.103%

    No Known Activations