© 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. 39031
    Prev
    Next
    INDEX
    Explanations

    proven track record

    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
    Ctl
    -0.09
    geber
    -0.08
    goo
    -0.08
    Ñĥни
    -0.08
    ÑĪиб
    -0.08
    æ¯Ĵ
    -0.08
    usz
    -0.08
    ods
    -0.08
    æŃ»åIJİ
    -0.08
    po
    -0.08
    POSITIVE LOGITS
     Ore
    0.10
    ä½ĵ系建设
    0.10
    ä¸įçĪ±
    0.09
    ably
    0.09
     proven
    0.09
    asi
    0.09
    ance
    0.09
    ria
    0.09
    ity
    0.09
    -effective
    0.09
    Activations Density 0.021%

    No Known Activations