© 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. 1179
    Prev
    Next
    INDEX
    Explanations

    health centers

    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
    ä¸ŃåĽ½ä¼ģä¸ļ
    -0.11
    æİĮ声
    -0.09
    ç»ĻæĪij
    -0.09
    rice
    -0.09
    èĩªåľ¨
    -0.08
    è§Ħ模以ä¸Ĭ
    -0.08
    èĤ¤
    -0.08
    (or
    -0.08
    åĽºçĦ¶
    -0.08
    acad
    -0.08
    POSITIVE LOGITS
    ä¹¡åľŁ
    0.09
    trail
    0.09
    alie
    0.08
     Ker
    0.08
    éĿ©æĸ°
    0.08
    æķĻèĤ²
    0.08
    iju
    0.08
    ç¥ģ
    0.08
    çĬ¯
    0.08
    森
    0.08
    Activations Density 0.079%

    No Known Activations