© 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. 32-TRANSCODER-HP
    7. 43076
    Prev
    Next
    INDEX
    Explanations

    science and research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ter
    -0.27
    âľĸ
    -0.25
    æĹĭ
    -0.25
    ç³Ļ
    -0.24
    SEP
    -0.24
    åħ«ä¸ª
    -0.24
    æŶä¸į
    -0.24
    éĶŁ
    -0.24
    enderit
    -0.23
    à¹ģà¸Ł
    -0.23
    POSITIVE LOGITS
    currentState
    0.29
    itz
    0.27
    artz
    0.25
    borg
    0.25
    好
    0.25
    tie
    0.24
    常åĬ¡
    0.24
    ãģŀ
    0.24
    linger
    0.24
    é±
    0.24
    Activations Density 0.004%

    No Known Activations