© 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. 33586
    Prev
    Next
    INDEX
    Explanations

    spending time or money

    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
    è·ĭ
    -0.11
    æĦ¤æĢĴ
    -0.09
    изаÑĨиÑı
    -0.09
    人éĻħ
    -0.09
    åħĪæĬĬ
    -0.09
    åģļä¸įåĪ°
    -0.09
    å°ĺ
    -0.08
    ured
    -0.08
    塵
    -0.08
    é¼ĵ
    -0.08
    POSITIVE LOGITS
    çļĦæ¯į亲
    0.10
    iagnostics
    0.09
    plier
    0.09
    éļ¾åħ³
    0.08
    Test
    0.08
     ante
    0.08
    çĨĺ
    0.08
    ush
    0.08
     roku
    0.08
     close
    0.08
    Activations Density 0.020%

    No Known Activations