© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20979
    Prev
    Next
    INDEX
    Explanations

    problems or questions needing solutions

    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
    ç«ĸ
    -0.09
    ç²Ĺ
    -0.09
    pty
    -0.08
    ä¸įæĸŃçļĦ
    -0.08
    åºŁ
    -0.08
    _EXPR
    -0.08
     Pty
    -0.08
    åģıåģı
    -0.08
    Ø´Ùģ
    -0.08
    éļıå¤Ħ
    -0.08
    POSITIVE LOGITS
    çĸijéļ¾
    0.16
    éļ¾é¢ĺ
    0.13
    çĸijæĥij
    0.12
    åĽ°æĥij
    0.11
    解çŃĶ
    0.11
    沸
    0.11
    éģĩåĪ°äºĨ
    0.10
    åıijå±ķä¸Ń
    0.10
    åĽ°éļ¾
    0.10
    åıijçİ°èĩªå·±
    0.10
    Activations Density 0.127%

    No Known Activations