© 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. 22269
    Prev
    Next
    INDEX
    Explanations

    describing books or publishers

    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·èįī
    -0.09
    BAT
    -0.08
    éĢģåĩº
    -0.08
    转载
    -0.08
    posted
    -0.08
    æ¡£æ¡Ī
    -0.07
     prematurely
    -0.07
    äºĺ
    -0.07
    çı©
    -0.07
    åĢ«
    -0.07
    POSITIVE LOGITS
    è¿Ļæľ¬ä¹¦
    0.12
     ISBN
    0.11
    ISBN
    0.11
    åĽ¾ä¹¦
    0.11
    æľ¬ä¹¦
    0.11
    笼
    0.10
     bestselling
    0.10
    çķħéĶĢ
    0.10
    .amazon
    0.10
    åĩºçīĪ社
    0.10
    Activations Density 0.091%

    No Known Activations