© 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. 54371
    Prev
    Next
    INDEX
    Explanations

    fund infrastructure, operates online, jobs build

    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
    ftware
    -0.11
    å¸Ľ
    -0.09
    åĢŁè´·
    -0.09
    avage
    -0.08
    æ¼Ĥæµģ
    -0.08
    æĶ¶æĶ¯
    -0.08
    ä»Ĺ
    -0.08
    亮
    -0.08
    äºĶéĩij
    -0.08
    ä¸įçĽ¸ä¿¡
    -0.08
    POSITIVE LOGITS
    çĶµåİĤ
    0.12
    çĶµä»·
    0.12
    çĶµç½ij
    0.11
    æ¸ħæ´ģèĥ½æºIJ
    0.11
    å¯ĩ
    0.10
    ç»Ŀç¼ĺ
    0.10
    åħ¬çĶ¨
    0.10
    æ¸ħæ´ģ
    0.09
    é£İçĶµ
    0.09
    è´Łèį·
    0.09
    Activations Density 0.217%

    No Known Activations