© 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. 20175
    Prev
    Next
    INDEX
    Explanations

    how can I

    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
    ä¹°çļĦ
    -0.09
    èĮĥ
    -0.08
     posted
    -0.08
    è¾ŀ
    -0.08
    å¨ĥ
    -0.08
     Crane
    -0.08
    èĽŃ
    -0.08
     Views
    -0.07
    Errors
    -0.07
    views
    -0.07
    POSITIVE LOGITS
    æľīå¾ħ
    0.11
    æĻ´
    0.10
    isle
    0.09
    illé
    0.09
    oref
    0.09
    åĢ¬
    0.09
    管çIJĨä¸Ńå¿ĥ
    0.09
    åıĹçģ¾
    0.09
    æĪijèĩªå·±
    0.08
    itic
    0.08
    Activations Density 0.006%

    No Known Activations