© 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. 21467
    Prev
    Next
    INDEX
    Explanations

    where then

    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
    åĪ°æľŁ
    -0.10
    亲çĪ±
    -0.08
    æ§İ
    -0.08
    çıŃ主任
    -0.08
    åľ¨åħ¨åĽ½
    -0.08
     linspace
    -0.08
    TC
    -0.08
    ä¸ŃéĢĶ
    -0.08
    å½ĵæŶ
    -0.08
    ç¦ħ
    -0.08
    POSITIVE LOGITS
    æ¼¾
    0.10
    ä¹Łä¸įæķ¢
    0.10
    mie
    0.10
    abis
    0.10
    åĨįå¤ļ
    0.09
    OLER
    0.09
    ç¬ĥ
    0.09
     stakes
    0.09
    sis
    0.09
    ope
    0.09
    Activations Density 0.054%

    No Known Activations