© 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. 7026
    Prev
    Next
    INDEX
    Explanations

    get there

    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
    abb
    -0.09
     Cop
    -0.09
    ç½ħ
    -0.09
    yer
    -0.08
    æİ¥åıĹ
    -0.08
    æĸ°é²ľ
    -0.08
    æĬĺ
    -0.08
    æĹºçĽĽ
    -0.08
     Saga
    -0.08
    Cop
    -0.08
    POSITIVE LOGITS
    æĬµè¾¾
    0.13
    éĢļå¾Ģ
    0.13
    åĪ°è¾¾
    0.12
    缮çļĦåľ°
    0.11
    è·¯ä¸Ĭ
    0.11
    ÌĢ
    0.10
    èµ°åĪ°
    0.10
     journey
    0.10
    è·µ
    0.10
    è¾¾åĪ°äºĨ
    0.10
    Activations Density 0.043%

    No Known Activations