© 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. 59037
    Prev
    Next
    INDEX
    Explanations

    numbers and quantity selectors

    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
    éŃij
    -0.09
    ych
    -0.09
    å±ĭ
    -0.08
    -www
    -0.08
    UNCH
    -0.08
    æķij人
    -0.08
    UCH
    -0.08
    èĽĬ
    -0.08
    秦çļĩ
    -0.08
    éĿŀ常çļĦ
    -0.08
    POSITIVE LOGITS
    _Impl
    0.09
    Datetime
    0.09
    åĪĩåħ¥
    0.09
    ç³Ł
    0.09
    éĢĤåIJĪ
    0.09
    津贴
    0.09
    ç»Ħ
    0.08
    åĪĩåħ¥çĤ¹
    0.08
    çĺ«
    0.08
    æ»ĭ润
    0.08
    Activations Density 0.035%

    No Known Activations