© 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. 56911
    Prev
    Next
    INDEX
    Explanations

    fast becoming or growing

    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
    å®Ļ
    -0.10
     wards
    -0.09
    ocal
    -0.08
    ä¸Ģæĸ¹éĿ¢
    -0.08
    åıªå¥½
    -0.08
     AAP
    -0.08
    9
    -0.08
    è´ŁåĢº
    -0.08
    6
    -0.08
    4
    -0.08
    POSITIVE LOGITS
    éĢIJæ¸IJ
    0.13
    åį³å°Ĩ
    0.13
    æŃ£åľ¨
    0.12
    æħ¢æħ¢
    0.12
    éĢIJæŃ¥
    0.12
    æ¸IJæ¸IJ
    0.11
    æĹ¥çĽĬ
    0.11
     becoming
    0.11
    éĢIJå¹´
    0.11
    åıijçĶŁåıĺåĮĸ
    0.11
    Activations Density 0.209%

    No Known Activations