© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9809
    Prev
    Next
    INDEX
    Explanations

    meet on or with

    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
    hots
    -0.08
     dÃły
    -0.08
    ä¹Łä¸įåı¯èĥ½
    -0.08
    à¸ĩ
    -0.08
    gue
    -0.08
    åĭī
    -0.08
    çĥĿ
    -0.08
     Guar
    -0.08
    ÑĪив
    -0.07
    oit
    -0.07
    POSITIVE LOGITS
    prising
    0.10
    azon
    0.10
    SION
    0.10
    好èݱåĿŀ
    0.10
    ril
    0.10
    rowser
    0.09
    åĨ·
    0.09
    _ATOMIC
    0.09
    æ¶Īè´¹åĵģ
    0.09
    rious
    0.09
    Activations Density 0.013%

    No Known Activations