© 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. 22504
    Prev
    Next
    INDEX
    Explanations

    description of features or aspects

    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
    åħ·ä½ĵæĥħåĨµ
    -0.10
    arest
    -0.09
    æĤĦæĤĦ
    -0.08
    ä»ĸå¦Ī
    -0.08
     ÑĤоÑĢ
    -0.08
    ä¸ĵé¢ĺ
    -0.08
    icine
    -0.08
    åĪĿæľŁ
    -0.07
    yc
    -0.07
    æĤĦçĦ¶
    -0.07
    POSITIVE LOGITS
    åĴĮåıijå±ķ
    0.10
    åŃº
    0.10
    èİ«è¿ĩäºİ
    0.09
    grp
    0.09
    zia
    0.09
    gable
    0.09
    诸å¦Ĥ
    0.08
    åIJĦä½į
    0.08
    庶
    0.08
    å°įæĸ¹
    0.08
    Activations Density 1.500%

    No Known Activations