© 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. 51173
    Prev
    Next
    INDEX
    Explanations

    interview

    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¸įçĦ¶
    -0.09
    rost
    -0.09
    çĶ³ãģĹ
    -0.08
    è¦ģä¸įçĦ¶
    -0.08
    åıijå±ķæł¼å±Ģ
    -0.08
    æŀľçĦ¶
    -0.08
    æ¯Ļ
    -0.08
    å·Ŀ
    -0.08
    ernet
    -0.08
     Emblem
    -0.08
    POSITIVE LOGITS
    è®°èĢħéĩĩ访
    0.15
    ä¸ĵ访
    0.14
    访è°Ī
    0.13
    请æķĻ
    0.12
    éĹ®
    0.11
    æľ¬æĬ¥è®°èĢħ
    0.11
     entrev
    0.11
    è®°èĢħ
    0.10
     interviewer
    0.10
    åIJijè®°èĢħ
    0.10
    Activations Density 0.220%

    No Known Activations