© 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. 10539
    Prev
    Next
    INDEX
    Explanations

    fur

    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
    liness
    -0.09
    ä¸Ģå¦Ĥ
    -0.09
    ³
    -0.09
     Cottage
    -0.09
    èĥ¡åŃIJ
    -0.09
    æ¢ĥ
    -0.09
    屿
    -0.08
    ski
    -0.08
    spark
    -0.08
    åıįä¹ĭ
    -0.08
    POSITIVE LOGITS
    FU
    0.09
     FU
    0.09
    ycin
    0.08
    åıijå±ķæ½ľåĬĽ
    0.08
    urd
    0.08
    IME
    0.08
    inch
    0.08
     Reviewed
    0.08
    iously
    0.08
    CSI
    0.08
    Activations Density 0.017%

    No Known Activations