© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 3520
    Prev
    Next
    INDEX
    Explanations

    community health services

    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
    溯æºIJ
    -0.09
    人çĶŁ
    -0.09
     parts
    -0.08
     Parts
    -0.08
    /css
    -0.08
    DIM
    -0.08
    人çĶŁçļĦ
    -0.08
    .stub
    -0.08
    ä¸İåħ¶ä»ĸ
    -0.08
    éĺŁä¼į
    -0.08
    POSITIVE LOGITS
    /community
    0.12
    社åĮº
    0.10
    åŁŃ
    0.10
    社åįĢ
    0.09
    iagnostics
    0.09
    åĩºåħ¥
    0.09
    é¢Ĩè¢ĸ
    0.08
     INCLUDING
    0.08
    äºķ
    0.08
    Community
    0.08
    Activations Density 0.053%

    No Known Activations