© 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. 17565
    Prev
    Next
    INDEX
    Explanations

    scrambling to do something

    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
    å®Į
    -0.10
    注å®ļ
    -0.10
    缺åı£
    -0.09
    ä»»æĢ§
    -0.09
    ÙĤر
    -0.09
    çªģçł´
    -0.09
     crest
    -0.09
    unch
    -0.08
     Kemp
    -0.08
    holds
    -0.08
    POSITIVE LOGITS
    è¸Ĭè·ĥ
    0.16
    äºī缸
    0.15
    æĢ¥äºİ
    0.12
    赶紧
    0.12
    æĬ¢
    0.12
    æĢ¥å¿Ļ
    0.12
    è¿«ä¸įåıĬå¾ħ
    0.12
    紧迫
    0.12
    çĶŁæĢķ
    0.11
    毫ä¸įçĬ¹è±«
    0.11
    Activations Density 0.048%

    No Known Activations