© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37004
    Prev
    Next
    INDEX
    Explanations

    gut and gutting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĻ°
    -0.11
    ä»»ä½ķæŶåĢĻ
    -0.10
    holders
    -0.10
    èħ¿
    -0.09
    lei
    -0.09
     Bek
    -0.09
     Chatt
    -0.09
    첩
    -0.09
    MENT
    -0.09
    åĽ¢éķ¿
    -0.09
    POSITIVE LOGITS
    ters
    0.17
    ierrez
    0.13
    ted
    0.13
    tings
    0.13
    ting
    0.12
    Ñĩа
    0.10
    EDGE
    0.10
    ties
    0.10
    éŃĦ
    0.09
    篦
    0.09
    Activations Density 0.012%

    No Known Activations