© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 61982
    Prev
    Next
    INDEX
    Explanations

    required or approved actions

    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
    åĽłä¸ºåľ¨
    -0.09
    å¤ļå¹´çļĦ
    -0.08
    ä¸Ģå¦ĤæĹ¢å¾Ģ
    -0.08
    æīĵç®Ĺ
    -0.08
    ç²²
    -0.08
    isch
    -0.08
    ä¸Ģåı·
    -0.08
    车ä¸Ĭ
    -0.08
    ä¸Ģå¦Ĥ
    -0.08
    çĿĢåĬĽæīĵéĢł
    -0.08
    POSITIVE LOGITS
    æīįåı¯ä»¥
    0.12
    审议
    0.10
    åıªèĥ½
    0.10
    ä¹Łåıªèĥ½
    0.10
    ä»»ä½ķä¸Ģ个
    0.09
    è§ij
    0.09
    ä»»ä½ķæĹ¶åĢĻ
    0.09
    åıĺæĽ´
    0.09
    ä¹Łåıªæľī
    0.09
    âĵĴ
    0.09
    Activations Density 0.040%

    No Known Activations