© 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. 9890
    Prev
    Next
    INDEX
    Explanations

    be found / be gained / be fought / be observed

    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
    æľĿ
    -0.11
     Nack
    -0.11
    åĪĹåħ¥
    -0.09
    æ»ķ
    -0.09
    绵
    -0.09
    为æĤ¨
    -0.09
    æĺ¥èĬĤæľŁéĹ´
    -0.09
    iciel
    -0.08
    DIC
    -0.08
    obby
    -0.08
    POSITIVE LOGITS
    æīĢèĥ½
    0.09
     ÑĢаÑģпол
    0.09
    forcer
    0.09
    æĴ·
    0.09
    åı¯è§Ĥ
    0.09
    uin
    0.08
    egr
    0.08
    available
    0.08
    éŸ
    0.08
    çĥŃéĩı
    0.08
    Activations Density 0.061%

    No Known Activations