© 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. 57046
    Prev
    Next
    INDEX
    Explanations

    tend to

    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
    ä¾ĿçĦ¶
    -0.10
    ä¾ĿçĦ¶æĺ¯
    -0.10
     RAT
    -0.09
    ç«Ł
    -0.09
    æľīä»»ä½ķ
    -0.09
    åĬŃ
    -0.09
    _bid
    -0.09
    åĿį
    -0.08
    ç«ŁçĦ¶
    -0.08
    å±ħçĦ¶
    -0.08
    POSITIVE LOGITS
    æ¯Ķè¾ĥå¤ļ
    0.11
    è¾ĥå¤ļ
    0.09
    æ¯Ķè¾ĥ
    0.09
    ivist
    0.09
    è¿ĩåĪĨ
    0.09
    FPS
    0.09
    ä¸į太
    0.09
    æ¯Ķè¾ĥç®Ģåįķ
    0.09
    èī¯
    0.09
     somewhat
    0.09
    Activations Density 0.042%

    No Known Activations