© 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. 58334
    Prev
    Next
    INDEX
    Explanations

    citation numbers and punctuation

    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
     ÑģÑĤо
    -0.09
    sha
    -0.09
    inct
    -0.08
    åħħ
    -0.08
    nable
    -0.08
    èĥ±
    -0.08
    è´¯
    -0.07
    pai
    -0.07
    åIJŀ
    -0.07
     Jude
    -0.07
    POSITIVE LOGITS
    ä¹Łä¸º
    0.11
    è¿Ļ让
    0.10
    åIJĮåŁİ
    0.09
    èĻļæŀĦ
    0.09
    å¾ĹçŁ¥
    0.08
    ä½Ĩå®ĥ
    0.08
    æħ
    0.08
    å§ĭ
    0.08
    LEAR
    0.08
    ä½ķå¿ħ
    0.08
    Activations Density 0.381%

    No Known Activations