© 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. 56240
    Prev
    Next
    INDEX
    Explanations

    moving away

    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
    æĤŁ
    -0.10
     вÑģÑı
    -0.09
    combe
    -0.09
    rzÄĻ
    -0.08
     каÑĩ
    -0.08
    icode
    -0.08
    衽
    -0.08
    çĸijä¼¼
    -0.08
    è£ľ
    -0.08
    ÑģÑĮ
    -0.08
    POSITIVE LOGITS
    eper
    0.09
    çĽ¾
    0.09
    aders
    0.08
    _ub
    0.08
    æľĢåĸľæ¬¢çļĦ
    0.08
    åģķ
    0.08
    æĹºçĽĽ
    0.08
    ç¾İ好çĶŁæ´»
    0.08
    åĮĹ京æŶéĹ´
    0.08
    齡
    0.08
    Activations Density 0.003%

    No Known Activations