© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8489
    Prev
    Next
    INDEX
    Explanations

    vague or difficult to define

    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¿¡æģ¯åħ¬å¼Ģ
    -0.10
    æµ´
    -0.09
    éĵĻ
    -0.09
    éķ£
    -0.09
    THR
    -0.09
     Huff
    -0.08
    åİŁåŀĭ
    -0.08
    æĬ¥éĶĢ
    -0.08
    èħĬ
    -0.08
    éŀŃ
    -0.08
    POSITIVE LOGITS
     neb
    0.14
    æĬ½è±¡
    0.13
    å®ı大
    0.12
    æ³Ľ
    0.12
    å®ıè§Ĥ
    0.11
     vague
    0.11
    æŀ¯çĩ¥
    0.11
     vag
    0.10
    å®ı
    0.10
    è®®é¢ĺ
    0.10
    Activations Density 0.090%

    No Known Activations