© 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. 18836
    Prev
    Next
    INDEX
    Explanations

    counselling and related services

    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
    ëģĶ
    -0.10
    adm
    -0.10
    htag
    -0.10
    dden
    -0.09
    æł·çļĦ
    -0.09
    heid
    -0.09
    ãĤĪãģĨãģª
    -0.09
    ãĥ¥
    -0.08
    ocard
    -0.08
    htags
    -0.08
    POSITIVE LOGITS
    виÑĤ
    0.10
    ÑĤÑĢ
    0.09
    çĭİ
    0.09
    maid
    0.09
    ÑĢов
    0.09
     Bray
    0.09
    ores
    0.08
    worth
    0.08
    èĴº
    0.08
    æĸ«
    0.08
    Activations Density 0.009%

    No Known Activations