© 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. 3908
    Prev
    Next
    INDEX
    Explanations

    copy permissions

    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
    les
    -0.10
    amel
    -0.09
     pinch
    -0.08
    åı¤ä»Ĭ
    -0.08
    antha
    -0.08
    èŁł
    -0.08
    æ·ĭ
    -0.08
    伸æīĭ
    -0.08
    -source
    -0.08
    -man
    -0.08
    POSITIVE LOGITS
    èĶļ
    0.10
    zsche
    0.09
    _MACRO
    0.08
    Ñĥв
    0.08
    ä»»ä½ķæŶåĢĻ
    0.08
    _Helper
    0.08
    iaux
    0.08
    .Sc
    0.08
    اÙĤ
    0.08
    å§Ŀ
    0.08
    Activations Density 0.076%

    No Known Activations