© 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. 50229
    Prev
    Next
    INDEX
    Explanations

    usher / coax

    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
    è®°èĢħ表示
    -0.09
    cient
    -0.09
    çľ¼ç¥ŀ
    -0.09
    olid
    -0.08
    èĸ°
    -0.08
    翼
    -0.08
    éĴĹ
    -0.08
    ãĥ©ãĤ¤
    -0.08
    igy
    -0.08
    ãĥªãĥ¼
    -0.08
    POSITIVE LOGITS
    ä¸ĭåįĬ
    0.10
    ãĤĴè¿İ
    0.10
    éĺµéĺµ
    0.10
    åĴĮæĶ¯æĮģ
    0.10
    eer
    0.09
    ãĤĴè¿İãģĪ
    0.09
    楹
    0.09
    æ¶ķ
    0.09
    ä¸įéĢļ
    0.09
    edList
    0.09
    Activations Density 0.005%

    No Known Activations