© 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. 57197
    Prev
    Next
    INDEX
    Explanations

    as such

    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
     however
    -0.12
    erie
    -0.10
    ç»ıèIJ¥æ´»åĬ¨
    -0.10
     ведÑĮ
    -0.10
    çĦ¶èĢĮ
    -0.10
    however
    -0.09
    èĦIJ
    -0.09
     jedoch
    -0.09
    æľī没æľī
    -0.08
    æīĢè°ĵçļĦ
    -0.08
    POSITIVE LOGITS
    æĺ¯ä»¥
    0.08
     goodness
    0.08
    å¾ģæ±Ĥ
    0.08
    æķĻç¨ĭ
    0.08
     doubly
    0.08
     Oval
    0.08
    ãĢģãĢģ
    0.07
    Ñģад
    0.07
    æ§Ľ
    0.07
     TAX
    0.07
    Activations Density 0.108%

    No Known Activations