© 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. 36275
    Prev
    Next
    INDEX
    Explanations

    added or additions

    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
    墨
    -0.11
    ingly
    -0.10
    ä¹İ
    -0.10
    oj
    -0.10
    æ¸ħéĨĴ
    -0.10
    igrations
    -0.09
    çİ°çĬ¶
    -0.09
    zcze
    -0.08
    为空
    -0.08
    æIJ¬å®¶
    -0.08
    POSITIVE LOGITS
    OrUpdate
    0.12
    ition
    0.11
    endum
    0.10
    /mod
    0.10
    åĴĮå®ĮåĸĦ
    0.09
    çļ±çº¹
    0.09
    ä¸Ģéģĵ
    0.09
    ITIONAL
    0.09
    itions
    0.08
    å·¥ä½ľå²Ĺä½į
    0.08
    Activations Density 0.084%

    No Known Activations