© 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. 50960
    Prev
    Next
    INDEX
    Explanations

    Locke, libertarian, created

    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
    ç»Ĵ
    -0.09
     bic
    -0.09
    stime
    -0.08
    è·Ł
    -0.08
    bic
    -0.08
    æ±°
    -0.08
     Gund
    -0.08
    еÑģп
    -0.08
     tab
    -0.08
     Specs
    -0.08
    POSITIVE LOGITS
    thro
    0.11
    ä¸ī代
    0.09
    å§Ķåijĺ
    0.09
    å®Į
    0.09
    ivery
    0.09
    imed
    0.09
    á»į
    0.08
    otypes
    0.08
    è°Ł
    0.08
    ลำ
    0.08
    Activations Density 0.006%

    No Known Activations