© 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. 52844
    Prev
    Next
    INDEX
    Explanations

    right or true

    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
    çĭ¬
    -0.09
    æīĺ
    -0.09
    á»ĥn
    -0.09
     Taj
    -0.09
    åıªçŁ¥éģĵ
    -0.08
    æĮĤåľ¨
    -0.08
    æĭľ
    -0.08
    è´¬
    -0.08
    åīª
    -0.08
    коп
    -0.08
    POSITIVE LOGITS
    侯
    0.10
    ollow
    0.09
    Į¨
    0.09
    浪
    0.09
    ildo
    0.09
    夫
    0.08
    使åij½
    0.08
    ç§ģãĤĤ
    0.08
    antar
    0.08
    åĢĻ
    0.08
    Activations Density 0.188%

    No Known Activations