© 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. 1691
    Prev
    Next
    INDEX
    Explanations

    link and hyperlinks

    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
    èĢģå¦Ī
    -0.10
    表çĻ½
    -0.10
    äºĨäºĽ
    -0.09
    è¾ĥå¿«
    -0.09
    uploader
    -0.09
    èĢ³è¾¹
    -0.09
    atus
    -0.09
    æĦĪ
    -0.09
    æķ´é¡¿
    -0.09
    æŶè£ħ
    -0.09
    POSITIVE LOGITS
     link
    0.19
    éĵ¾æİ¥
    0.18
     links
    0.18
    ãĥªãĥ³ãĤ¯
    0.17
    _links
    0.15
    link
    0.15
     ÑģÑģÑĭл
    0.15
    .link
    0.14
    alink
    0.14
    -links
    0.14
    Activations Density 0.303%

    No Known Activations