© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 49846
    Prev
    Next
    INDEX
    Explanations

    porn star

    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
    ä¸ĩ家
    -0.09
     Monument
    -0.09
    pects
    -0.09
    åİĿ
    -0.09
    enga
    -0.08
    ãģ¨ãģĨ
    -0.08
    RATE
    -0.08
     Ñĥзн
    -0.08
    ä¸Ģå®ļçļĦ
    -0.08
     اÙĦØ£ÙħÙĨ
    -0.08
    POSITIVE LOGITS
    ographic
    0.12
    isode
    0.09
    ishly
    0.09
    اء
    0.09
    使æĪij
    0.09
    çķĮçļĦ
    0.09
    ish
    0.09
    iques
    0.08
    wik
    0.08
    oland
    0.08
    Activations Density 0.005%

    No Known Activations