© 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. 31759
    Prev
    Next
    INDEX
    Explanations

    duration or time spent

    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®ĭå¿į
    -0.09
    elsen
    -0.09
    hek
    -0.09
    稳å®ļçļĦ
    -0.09
     Petr
    -0.09
    reta
    -0.09
    樹
    -0.09
    æİ¥è¿ĩ
    -0.09
    çĵ·
    -0.08
    èĶ«
    -0.08
    POSITIVE LOGITS
    åĬłçıŃ
    0.20
    çĨ¬å¤ľ
    0.19
    åĩĮæĻ¨
    0.17
    æ·±å¤ľ
    0.17
    å¤ľ
    0.16
    è¿ŀå¤ľ
    0.15
    å¤ľæĻļ
    0.14
    æĺ¼å¤ľ
    0.14
    å¤ľéĹ´
    0.13
    å¤ľéĩĮ
    0.13
    Activations Density 0.048%

    No Known Activations