© 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. 39978
    Prev
    Next
    INDEX
    Explanations

    ten followed by specific nouns

    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
    åŀĴ
    -0.09
    ä½Ĩä»į
    -0.08
    ä½¼
    -0.08
    ãĥ¬ãĤ¤
    -0.08
    umm
    -0.08
    /from
    -0.08
    written
    -0.08
    lops
    -0.08
    åĨį次
    -0.08
    eil
    -0.08
    POSITIVE LOGITS
    itivity
    0.09
    ctl
    0.09
    èģĮä¸ļçĶŁæ¶¯
    0.09
    arium
    0.09
    ç©´
    0.09
    è§Ĩéĩİ
    0.08
    éĤĢ
    0.08
    éģĵçIJĨ
    0.08
    .Ref
    0.08
    ç²¾å¯Ĩ
    0.08
    Activations Density 0.076%

    No Known Activations