© 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. 50671
    Prev
    Next
    INDEX
    Explanations

    circle related terms

    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
    ility
    -0.12
    ness
    -0.10
    arak
    -0.09
    ent
    -0.08
    nbsp
    -0.08
    re
    -0.08
    ç½¾
    -0.08
    ðŁı»
    -0.08
    IOS
    -0.08
    semble
    -0.08
    POSITIVE LOGITS
    åľĪ
    0.14
    åŃIJéĩĮ
    0.13
    ander
    0.11
    arity
    0.11
    âŃķ
    0.11
    nder
    0.10
    ä¸ĢåľĪ
    0.10
    icals
    0.10
    (circle
    0.10
    ULAR
    0.10
    Activations Density 0.024%

    No Known Activations