© 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. 62163
    Prev
    Next
    INDEX
    Explanations

    anyone or everyone

    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
    è¿İ
    -0.09
     Horton
    -0.09
    ä»»
    -0.09
    åħ¨æ°ij
    -0.08
    对çĿĢ
    -0.08
    带ç»Ļ
    -0.08
     Spo
    -0.08
    è¿ĺæľī
    -0.08
    ç»ĻäºĨ
    -0.07
    trak
    -0.07
    POSITIVE LOGITS
    æĦŁåħ´è¶£
    0.10
    稳åģ¥
    0.10
    æľīåħ´è¶£
    0.10
     interested
    0.09
    åĤ¥
    0.09
    CurrentValue
    0.09
    åıijå±ķä¸Ń
    0.09
     инÑĤеÑĢеÑģ
    0.09
    éĸ
    0.09
    Interested
    0.09
    Activations Density 0.012%

    No Known Activations