© 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. 34626
    Prev
    Next
    INDEX
    Explanations

    to achieve or maintain

    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
    ç«ŀ
    -0.09
    å·į
    -0.08
    sworth
    -0.08
    APO
    -0.08
    æĽ´éĩįè¦ģ
    -0.08
    æİ¡
    -0.08
    éĢīæĭ©äºĨ
    -0.08
    oso
    -0.08
    éĩĩ
    -0.08
     вÑĭÑĢажен
    -0.08
    POSITIVE LOGITS
    便äºİ
    0.16
    ç¡®ä¿Ŀ
    0.13
    éģ¿åħį
    0.11
    以便
    0.11
    æĸ¹ä¾¿
    0.11
    帮åĬ©
    0.11
    å°½éĩı
    0.11
    使åħ¶
    0.11
    è¿İåIJĪ
    0.10
    allow
    0.10
    Activations Density 0.167%

    No Known Activations