© 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. 57292
    Prev
    Next
    INDEX
    Explanations

    declaration, emergency, ordinance, state of siege

    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
     trick
    -0.10
    çĥŃ
    -0.10
    çī¢åĽº
    -0.09
    çĥŃæĥħ
    -0.09
    okit
    -0.09
    ож
    -0.09
    èĻIJå¾ħ
    -0.09
    åįĩ级æĶ¹éĢł
    -0.09
    èµ·è¯ī
    -0.09
    æµģåĩº
    -0.09
    POSITIVE LOGITS
    ç´§æĢ¥
    0.12
    åºĶæĢ¥
    0.11
     emergency
    0.10
    Susp
    0.10
    emergency
    0.09
    æݥ管
    0.09
    åĬ¨åijĺ
    0.09
    æ·ĺ
    0.09
     declaration
    0.09
     mating
    0.09
    Activations Density 0.078%

    No Known Activations