© 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. 18569
    Prev
    Next
    INDEX
    Explanations

    statistical regression and analysis

    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
    æĪĽ
    -0.10
    æľį
    -0.09
    人寿
    -0.09
    人çĶŁ
    -0.08
    åĬ¨åijĺ
    -0.08
    ACEMENT
    -0.08
    _FRE
    -0.08
    .Dot
    -0.08
    minate
    -0.08
    mad
    -0.08
    POSITIVE LOGITS
     Haz
    0.11
    åį±éĻ©
    0.10
    ä¿Ŀåģ¥
    0.09
     Cabin
    0.09
     hazard
    0.09
    ä¸įæŃ»
    0.09
    Haz
    0.09
    æ³Ħæ¼ı
    0.09
    大åıĶ
    0.09
    é£İéĻ©
    0.09
    Activations Density 0.315%

    No Known Activations