© 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. 95584
    Prev
    Next
    INDEX
    Explanations

    grammar

    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
    ละ
    -0.28
    ago
    -0.27
     eag
    -0.26
    æŶåħī
    -0.25
    arga
    -0.25
    æŁ¥å°ģ
    -0.25
    è®®
    -0.25
    è¡Ķ
    -0.25
    åºŃéĻ¢
    -0.24
    ç¿©
    -0.24
    POSITIVE LOGITS
     rules
    0.32
    rules
    0.32
     rule
    0.28
    _rules
    0.28
    okia
    0.28
    olia
    0.28
    åıijå±ķ模å¼ı
    0.27
     Rules
    0.26
    olley
    0.26
    HAM
    0.26
    Activations Density 0.109%

    No Known Activations