© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19441
    Prev
    Next
    INDEX
    Explanations

    too early, too old, too late, too many

    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¸įæĥľ
    -0.10
    å±ł
    -0.09
    çĸı
    -0.09
    èĬ¸
    -0.09
    ä»Ĺ
    -0.09
    磼
    -0.09
    鸣
    -0.08
    åĨ¶çĤ¼
    -0.08
    并ä¸İ
    -0.08
    åı¯èĥ½åĩºçİ°
    -0.08
    POSITIVE LOGITS
     nor
    0.10
    éĥ½ä¸įèĥ½
    0.10
    ä¹Łä¸įè¦ģ
    0.09
     Lair
    0.09
    aget
    0.09
    ãĥ©ãĥ³ãĥī
    0.09
    ä¸Ģ个好çļĦ
    0.09
    ä¸ĵç§ij
    0.08
    ropol
    0.08
    éĤ»å±ħ
    0.08
    Activations Density 0.010%

    No Known Activations