© 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. 43770
    Prev
    Next
    INDEX
    Explanations

    Beginning of texts

    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
    éĢģåĩº
    -0.27
    .ReadFile
    -0.26
    perc
    -0.25
    çĴIJ
    -0.25
    ç¥ł
    -0.25
    TabControl
    -0.25
    æİĮæı¡
    -0.24
    tab
    -0.24
     duplex
    -0.24
    apas
    -0.24
    POSITIVE LOGITS
    PTY
    0.33
    æ¿ł
    0.31
    ivor
    0.28
    Smith
    0.28
    bour
    0.26
     interruption
    0.26
    oir
    0.26
     ide
    0.25
    Ide
    0.25
    tery
    0.25
    Activations Density 0.000%

    No Known Activations