© 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. 35874
    Prev
    Next
    INDEX
    Explanations

    lock

    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
    èµ°ç§ģ
    -0.10
    æŁĺ
    -0.09
    移éĢģ
    -0.09
    odia
    -0.09
    ä¸įçĶ±
    -0.09
    èĪ¸
    -0.09
    earch
    -0.09
    æİĸ
    -0.08
    æīĢåľ¨åľ°
    -0.08
    ATIC
    -0.08
    POSITIVE LOGITS
    .lock
    0.13
    éĶģå®ļ
    0.12
     locks
    0.12
    åħ±äº«
    0.12
     lock
    0.12
    -lock
    0.11
    lock
    0.11
    éĶģ
    0.11
     LOCK
    0.11
    	lock
    0.11
    Activations Density 0.187%

    No Known Activations