© 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. 18750
    Prev
    Next
    INDEX
    Explanations

    increase speed or number

    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
     geopol
    -0.09
    _reduction
    -0.09
    rib
    -0.09
    è¿Ľå±ķ
    -0.08
    æľ¬èº«å°±æĺ¯
    -0.08
    æİī
    -0.08
    ç²²
    -0.08
    Composition
    -0.08
    composition
    -0.08
    çļĦæĢģ度
    -0.08
    POSITIVE LOGITS
    æĽĿåħī
    0.13
    çŁ¥åIJį度
    0.12
    è§ģè¯Ĩ
    0.12
    责任æĦŁ
    0.12
    /de
    0.11
    éļ¾åº¦
    0.11
    åħįçĸ«åĬĽ
    0.11
    å·¥ä½ľæķĪçİĩ
    0.10
    _capabilities
    0.10
    çŁ¥æĻĵ
    0.10
    Activations Density 0.227%

    No Known Activations