© 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. 50798
    Prev
    Next
    INDEX
    Explanations

    calculator, roller, game, attend

    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
    ä¸ĭæīĭ
    -0.09
    æĬij
    -0.09
    å°Ĩåħ¶
    -0.08
    çŁ¥æĻĵ
    -0.08
    å®£ä¼ł
    -0.08
    åıĮåıĮ
    -0.08
    çݰ身
    -0.07
    å½ĵåľ°æĶ¿åºľ
    -0.07
    hone
    -0.07
    æħij
    -0.07
    POSITIVE LOGITS
    对æĪijæĿ¥è¯´
    0.10
    å¾Īé«ĺåħ´
    0.10
    orer
    0.10
    çĮľ
    0.10
    eve
    0.10
    æĪijæĺ¯
    0.09
    ä¹Łæľīå¾Īå¤ļ
    0.09
    ROLLER
    0.09
    è·Łä½ł
    0.09
    ForResource
    0.09
    Activations Density 0.035%

    No Known Activations