© 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. 48805
    Prev
    Next
    INDEX
    Explanations

    food imports

    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
    Capability
    -0.08
    ä¸į解
    -0.08
    Latch
    -0.08
    主åĬĽåĨĽ
    -0.08
    èįī
    -0.08
    æ¯ıå¹´éĥ½
    -0.08
    ardo
    -0.07
     ambigu
    -0.07
    æľ¬èĥ½
    -0.07
     Gord
    -0.07
    POSITIVE LOGITS
    éĬ®
    0.12
    åľ°æłĩ
    0.11
    æIJľæķij
    0.11
    没äºĭ
    0.10
    éķ¿æķĪ
    0.10
    饯
    0.10
    ellas
    0.10
    èĥ´
    0.10
    æ®ĭçķĻ
    0.10
    åıĸè¯ģ
    0.10
    Activations Density 0.088%

    No Known Activations