© 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. 27426
    Prev
    Next
    INDEX
    Explanations

    expressions of opinion or observation

    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
    çľĭä¸įè§ģ
    -0.09
    åĽłä¸ºæĪij们
    -0.08
    åĽłä¸ºåľ¨
    -0.08
    çĶ±äºİ
    -0.08
    åĽłä¸º
    -0.08
    Cu
    -0.08
     obviously
    -0.08
     distinguish
    -0.08
    èĬ±äºĨ
    -0.08
    voices
    -0.08
    POSITIVE LOGITS
    è¿Ļä¹Īåģļ
    0.11
    è¿Ļä¸ĢçĤ¹
    0.11
    è¦ģåģļåĪ°
    0.10
    ä¹Łä¸įæĥ³
    0.10
    绡
    0.09
    æŃ¤é¡¹
    0.09
    è§Ĭ
    0.09
    è¿Ļæł·åģļ
    0.09
    æīįè¡Į
    0.09
    /channel
    0.09
    Activations Density 0.114%

    No Known Activations