© 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. 20062
    Prev
    Next
    INDEX
    Explanations

    ок .k ktop Kot Records

    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
    æ¸Ĭ
    -0.09
    smith
    -0.09
    ç¼ĺ
    -0.09
    è¿Ļå¼ł
    -0.09
    reds
    -0.08
     duy
    -0.08
     Sne
    -0.08
    ç·£
    -0.08
    åį«çĶŁ
    -0.08
     наÑĢ
    -0.08
    POSITIVE LOGITS
    ç§ijæĬĢèĤ¡ä»½
    0.12
    åħĭ
    0.12
    ktop
    0.12
    æ¹ĸ
    0.11
    ãģį
    0.11
    _k
    0.11
    Ùĥات
    0.11
    кова
    0.11
     K
    0.11
    íģ¬
    0.11
    Activations Density 0.281%

    No Known Activations