© 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. 38065
    Prev
    Next
    INDEX
    Explanations

    lists of items

    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
    åĥ¦
    -0.10
    å½·
    -0.09
     Bacon
    -0.09
    åĪĿå¿ĥ
    -0.08
    maj
    -0.08
    rones
    -0.08
    樾
    -0.08
    reck
    -0.08
    Ä°N
    -0.08
    unfold
    -0.08
    POSITIVE LOGITS
    ç»ĵæŀĦè°ĥæķ´
    0.09
    åĮºåŁŁæĢ§
    0.09
    aison
    0.08
    æĸ¼æĺ¯
    0.08
    è¿Ļæĸ¹éĿ¢
    0.08
    CursorPosition
    0.08
    人å±ħ
    0.08
    æīĢéľĢè¦ģçļĦ
    0.08
    çģ¾
    0.08
    è¿ĽèĢĮ
    0.08
    Activations Density 0.620%

    No Known Activations