© 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. 39211
    Prev
    Next
    INDEX
    Explanations

    new range, arms, pass, hair, game, characters, head, foster

    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
    æĹ¥åIJİ
    -0.10
    è¿ĩå¾Ģ
    -0.09
    çļĦä¸ĢåĪĩ
    -0.09
    èļ¬
    -0.09
    xia
    -0.09
    ä»ħ代表
    -0.09
    åIJİæľŁ
    -0.08
    å¥ķ
    -0.08
    xmm
    -0.08
    ä½ķæŶ
    -0.08
    POSITIVE LOGITS
    ä»Ļ
    0.09
    éĩijåĪļ
    0.09
    è¿Ļå¼ł
    0.09
    bell
    0.09
    çķ¥æľī
    0.08
    /original
    0.08
     IHttp
    0.08
    é¢ĵ
    0.08
    æīĵæ³ķ
    0.08
    .addListener
    0.08
    Activations Density 0.044%

    No Known Activations