© 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. 35428
    Prev
    Next
    INDEX
    Explanations

    zinc, inc

    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
    åħ³ç¾½
    -0.11
    åĨ¥
    -0.10
    æ²¾
    -0.10
    roe
    -0.10
    æļ¹
    -0.10
    andest
    -0.09
    äºijéĽĨ
    -0.09
    çĺ¿
    -0.09
    å¥Ħ
    -0.09
    ë°¸
    -0.09
    POSITIVE LOGITS
    æĸĹ
    0.10
     trick
    0.09
    çĪĨ
    0.09
    åįĸåľº
    0.08
    èĪŁ
    0.08
    饺
    0.08
     broad
    0.08
    èĤļ
    0.08
    zes
    0.08
    anine
    0.08
    Activations Density 0.066%

    No Known Activations