© 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. 56354
    Prev
    Next
    INDEX
    Explanations

    create, add, destroy value

    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
    åįıè°ĥåıijå±ķ
    -0.10
    è±ģ
    -0.09
    cala
    -0.09
    ä»Ģä¹Īéĥ½ä¸į
    -0.09
    PL
    -0.09
    å¥
    -0.09
    ä¹ĭéĻħ
    -0.08
    æ²ĵ
    -0.08
    è´¹çİĩ
    -0.08
    oron
    -0.08
    POSITIVE LOGITS
    ä»·åĢ¼
    0.18
     value
    0.13
    å¢ŀåĢ¼
    0.13
    åĥ¹åĢ¼
    0.12
    (value
    0.12
    value
    0.12
    éĻĦåĬłåĢ¼
    0.11
     VALUE
    0.11
    çļĦä»·åĢ¼
    0.11
    価
    0.11
    Activations Density 0.043%

    No Known Activations