© 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. 41461
    Prev
    Next
    INDEX
    Explanations

    UI elements

    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
    ä¹ĹãĤĬ
    -0.29
    Sil
    -0.29
    lok
    -0.28
    лив
    -0.27
    irc
    -0.26
    sil
    -0.26
     ranges
    -0.26
    modal
    -0.26
    lig
    -0.26
    .pop
    -0.26
    POSITIVE LOGITS
     organizer
    0.28
     controller
    0.27
    DownList
    0.27
    管æݧ
    0.26
    (Control
    0.26
    æݧåĪ¶ç³»ç»Ł
    0.26
    æݧåĪ¶åĻ¨
    0.26
     cabinet
    0.26
    oho
    0.26
    æݧåĪ¶
    0.26
    Activations Density 0.009%

    No Known Activations