© 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. 21560
    Prev
    Next
    INDEX
    Explanations

    mailto:

    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
    TAIL
    -0.10
    tech
    -0.09
    å¿ĥä¸Ń
    -0.09
    ritable
    -0.09
    tail
    -0.09
    bies
    -0.09
    设ç«ĭ
    -0.09
     breath
    -0.09
    tails
    -0.09
    ä¹Ŀ大
    -0.09
    POSITIVE LOGITS
    æµĨ
    0.09
    sembled
    0.09
     import
    0.08
    emia
    0.08
    æ°ĽåĽ´
    0.08
    éĢłåģĩ
    0.08
    otime
    0.08
    å®Ŀ
    0.08
    åĩĨæŶ
    0.08
    æ°Ķæ°Ľ
    0.08
    Activations Density 0.006%

    No Known Activations