© 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. 10336
    Prev
    Next
    INDEX
    Explanations

    exceed or below thresholds

    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
    åIJ¬å¾Ĺ
    -0.09
    è¿©
    -0.09
    é¹ī
    -0.09
    ability
    -0.09
    åĨ¼
    -0.08
    ç±į
    -0.08
     NPC
    -0.08
    èĬĿ
    -0.08
    IFE
    -0.08
    åĪĪ
    -0.08
    POSITIVE LOGITS
    è¶ħè¿ĩäºĨ
    0.16
    è¶ħåĩº
    0.15
    è¶ħè¿ĩ
    0.15
     exceeded
    0.14
    éĺĪ
    0.14
    ä½İäºİ
    0.14
     exceed
    0.13
     vượt
    0.13
    ãĤĴè¶ħãģĪ
    0.13
     exceeds
    0.13
    Activations Density 0.148%

    No Known Activations