© 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. 50223
    Prev
    Next
    INDEX
    Explanations

    mellowed / muted / back

    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
    ually
    -0.10
    bling
    -0.10
    itive
    -0.09
    adian
    -0.09
    lash
    -0.08
    æ³Ľ
    -0.08
    çķ¥
    -0.08
    åı£ä¸Ń
    -0.08
    alent
    -0.08
     slight
    -0.08
    POSITIVE LOGITS
    est
    0.11
    à¹Ĩ
    0.10
    认è¯ĨåĪ°
    0.10
    æľĪä¸Ń
    0.10
    çı©
    0.10
    èĦ¾æ°Ķ
    0.09
     à¹Ĩ
    0.09
    æľĪåĪĿ
    0.09
    æĥħ人
    0.09
    å¸Ĥåľºç«ŀäºī
    0.09
    Activations Density 0.002%

    No Known Activations