© 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. 33805
    Prev
    Next
    INDEX
    Explanations

    Arduino and processing programming

    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
    åĪ¹
    -0.09
    ç²ī
    -0.09
    HD
    -0.09
    imin
    -0.09
    æİĴ污
    -0.09
    å¸ĥ
    -0.09
    æĥİ
    -0.08
     worthless
    -0.08
    åħĪè¿Ľ
    -0.08
    çij·
    -0.08
    POSITIVE LOGITS
    licht
    0.09
    unner
    0.09
    onical
    0.09
    åĩºå·®
    0.08
    ä¸ĩåįĥ
    0.08
    ç¾İèĤ¡
    0.08
     пÑĥ
    0.08
    åħ»èĢģ
    0.08
    æ¢ħ西
    0.08
    éĢģ
    0.08
    Activations Density 0.128%

    No Known Activations