© 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. 61636
    Prev
    Next
    INDEX
    Explanations

    debated or criticized issues

    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
    _bits
    -0.09
    пад
    -0.09
    ä¸ĵä¸ļä»İäºĭ
    -0.09
    æĤ¨çļĦåŃ©åŃIJ
    -0.09
    èªĬ
    -0.09
    -original
    -0.09
    æĢİä¹Īçľĭ
    -0.08
    èģĺçĶ¨
    -0.08
     tasted
    -0.08
    sortable
    -0.08
    POSITIVE LOGITS
    ä¿ĥ使
    0.11
    使å¾Ĺ
    0.10
    ä¿ĥæĪIJ
    0.10
    æݨåĬ¨
    0.09
    åİĭåĬĽ
    0.09
    wers
    0.09
    äºīåıĸ
    0.09
    å¹²é¢Ħ
    0.09
    åĩłåı¥
    0.09
    åĬªåĬĽ
    0.09
    Activations Density 0.062%

    No Known Activations