© 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. 2346
    Prev
    Next
    INDEX
    Explanations

    evolution, history, development

    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
    æ°Ķæ°Ľ
    -0.11
    å¹³æŶ
    -0.09
    åıijåĩº
    -0.09
    èIJ¥åķĨ
    -0.09
     Svens
    -0.09
    èŀį
    -0.09
    çĽĬ
    -0.09
    _DAC
    -0.08
    plat
    -0.08
    bsub
    -0.08
    POSITIVE LOGITS
    æ¼Ķåıĺ
    0.15
    ä¸ĢæŃ¥æŃ¥
    0.15
    åıĺè¿ģ
    0.13
    åħĪæĺ¯
    0.13
    æ¼Ķ
    0.13
    åıĺåĮĸ
    0.13
    åıijå±ķ
    0.12
    æĺ¯ä»İ
    0.12
    åıijå±ķçļĦ
    0.11
    ä¸įæĸŃåıijå±ķ
    0.11
    Activations Density 0.229%

    No Known Activations