© 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. 35791
    Prev
    Next
    INDEX
    Explanations

    power line

    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®ļæľŁ
    -0.09
    åıĹ访
    -0.09
    ä¸ĬéŨ
    -0.09
     завод
    -0.09
     Marsh
    -0.08
    è¿ĩéĶĻ
    -0.08
    Marsh
    -0.08
    迹
    -0.08
    RefCount
    -0.08
    /functions
    -0.08
    POSITIVE LOGITS
    éĺ´
    0.11
    æĥħæĢĢ
    0.10
    æī¬å°ĺ
    0.10
    å¤ĸçķĮ
    0.09
    Ñģли
    0.09
    çĵ´
    0.09
    ä¸ī人
    0.09
    åİĨæĿ¥
    0.09
    è¹ī
    0.09
    rac
    0.09
    Activations Density 0.116%

    No Known Activations