© 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. 49264
    Prev
    Next
    INDEX
    Explanations

    this followed by description

    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
    èĤĩ
    -0.11
    æ¦Ľ
    -0.10
    æĭĪ
    -0.10
    atial
    -0.09
    æ¯ĶåĪ©
    -0.09
    è¿Ļä¸Ģå¹´
    -0.09
    æŃ¤æ¬¡æ´»åĬ¨
    -0.09
    ова
    -0.09
    åĬłéĩį
    -0.09
    å¶Ĥ
    -0.09
    POSITIVE LOGITS
    常è§ģ
    0.08
    åİ¢
    0.08
    ìľł
    0.08
    çīĿ
    0.08
    lore
    0.07
    å¼Ģåľº
    0.07
    æ°¸è¿ľä¸įä¼ļ
    0.07
    DOT
    0.07
    æ··åIJĪ
    0.07
    èĪ¶
    0.07
    Activations Density 0.124%

    No Known Activations