© 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. 11054
    Prev
    Next
    INDEX
    Explanations

    helpful tips

    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
    çĴŀ
    -0.09
    è§īæĤŁ
    -0.09
    çļĦæĦŁæĥħ
    -0.09
    ç±³å°Ķ
    -0.09
    æ±Łæ·®
    -0.08
    çļĦè®¤çŁ¥
    -0.08
    ç¿İ
    -0.08
    èĭķ
    -0.08
    çģ¿
    -0.08
    çģ¿çĥĤ
    -0.08
    POSITIVE LOGITS
     tips
    0.21
    tips
    0.19
    æĬĢå·§
    0.17
     Tips
    0.17
    Tips
    0.17
     ÑģовеÑĤ
    0.13
     useful
    0.12
    å®ŀçĶ¨
    0.12
    à¹Ģà¸Ĺà¸Ħà¸Ļ
    0.11
     techniques
    0.11
    Activations Density 0.070%

    No Known Activations