© 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. 49942
    Prev
    Next
    INDEX
    Explanations

    so followed by intensifier

    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
    æİ¥åıĹ
    -0.09
    æİ¥åıĹäºĨ
    -0.08
    è¾ĥå¿«
    -0.08
    วà¸Ļ
    -0.08
    æķ£çĥŃ
    -0.08
    å¹²äºĭ
    -0.08
    ä¸įä»ħä»ħ
    -0.08
    宿
    -0.08
    äºļ马éĢĬ
    -0.08
    æ¯Ķè¾ĥå¤ļ
    -0.08
    POSITIVE LOGITS
    èĿĩ
    0.09
    è¡Įç¨ĭ
    0.09
    eted
    0.09
    ars
    0.09
    åĩłæ¬¡
    0.09
    沸èħ¾
    0.08
    ugs
    0.08
    TEAM
    0.08
    åīĸæŀIJ
    0.08
    oose
    0.08
    Activations Density 0.024%

    No Known Activations