© 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. 5464
    Prev
    Next
    INDEX
    Explanations

    sufism sheemish commentary rotations strict

    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
    æ½®
    -0.11
    èĢľ
    -0.10
    åĨĻçļĦ
    -0.09
    ä¸ŃåĽ½æĶ¿åºľ
    -0.08
    被åĬ¨
    -0.08
    æķ¬è¯·
    -0.08
     Frag
    -0.08
    è¢ĸ
    -0.08
    çĬ
    -0.08
    æĪĸå°Ĩ
    -0.08
    POSITIVE LOGITS
    åĪ³
    0.10
    ç¦ħ
    0.10
    ÑĤÑĢо
    0.09
    æ³¼
    0.09
    éģĴ
    0.09
    æģ¬
    0.09
    æĸ«
    0.09
    æİĬ
    0.08
    ession
    0.08
    æ·±å±Ĥ次
    0.08
    Activations Density 0.028%

    No Known Activations