© 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. 26723
    Prev
    Next
    INDEX
    Explanations

    like the

    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
    å¿ĥæĻº
    -0.10
    ensive
    -0.09
    åĵªæĢķæĺ¯
    -0.09
     whatsoever
    -0.08
    åį¡æĭī
    -0.08
    è¦ģæĺ¯
    -0.08
     enr
    -0.08
    çľĭä¼¼
    -0.08
    æŁ¥çľĭ详æĥħ
    -0.08
    å¸ĺ
    -0.08
    POSITIVE LOGITS
    对å¾ħ
    0.11
    -minded
    0.10
    pri
    0.09
    éĤ£æł·
    0.09
    ãĤĭãĤĪãģĨãģ«
    0.09
    ä¸Ģæł·
    0.09
     sands
    0.08
    溶解
    0.08
    å¾Ģå¹´
    0.08
     Priest
    0.08
    Activations Density 0.130%

    No Known Activations