© 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. 50547
    Prev
    Next
    INDEX
    Explanations

    working titles or proper names

    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
    ogra
    -0.08
    è¦ģ说
    -0.08
    oute
    -0.08
    åĨį说
    -0.08
    æīĢè¬Ĥ
    -0.08
    æĶ¯æĮģ
    -0.08
     Wax
    -0.08
     Miy
    -0.08
     nodeList
    -0.08
    çıł
    -0.08
    POSITIVE LOGITS
    åIJįåŃĹ
    0.41
    çļĦåIJįåŃĹ
    0.40
    åIJį称
    0.38
     name
    0.34
    è¿Ļ个åIJįåŃĹ
    0.31
     ìĿ´ë¦Ħ
    0.29
     names
    0.29
     название
    0.28
    name
    0.27
    å§ĵåIJį
    0.26
    Activations Density 0.297%

    No Known Activations