© 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. 21895
    Prev
    Next
    INDEX
    Explanations

    family roles and relationships

    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
    æ³ķè§Ħ
    -0.09
    没人
    -0.09
    éĺµ
    -0.09
    å¸Ĥåľºä¸Ĭ
    -0.09
    ifa
    -0.09
    å±ķå¼Ģ
    -0.09
    满
    -0.09
    objs
    -0.09
    è³
    -0.09
    æīĵåİĭ
    -0.09
    POSITIVE LOGITS
    æĤĮ
    0.10
    ewise
    0.09
    æľįä»İ
    0.09
    åīľ
    0.09
    ToWorld
    0.09
    媳
    0.09
    çļĦè§Ĵ度
    0.08
    æīĢéľĢè¦ģ
    0.08
    çĶŁæĹ¥
    0.08
     kepada
    0.08
    Activations Density 0.045%

    No Known Activations