© 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. 38027
    Prev
    Next
    INDEX
    Explanations

    wearing clothing descriptions

    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
    å¾ĹåĪĨ
    -0.10
    semblies
    -0.09
    éĵ¿
    -0.09
    è¿Ļéĥ¨åĪĨ
    -0.09
    fé
    -0.09
    çĶ¨é¤IJ
    -0.09
    (qu
    -0.09
    认为
    -0.08
    å¤
    -0.08
    prung
    -0.08
    POSITIVE LOGITS
    /on
    0.10
    æĮĤçĿĢ
    0.09
    çĿĢéĩį
    0.09
    æĪijéĻ¢
    0.09
    ä»Ģä¹Īåij¢
    0.09
    ä¸ĢåĿĹ
    0.08
    åħ¨æĹ¥
    0.08
    æ°Ĺãģ«
    0.08
    ä¸Ģ个éĩįè¦ģ
    0.08
    اخ
    0.08
    Activations Density 0.033%

    No Known Activations