© 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. 8675
    Prev
    Next
    INDEX
    Explanations

    how about / what about

    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
    误ä¼ļ
    -0.10
    ye
    -0.09
    磼
    -0.09
    çľģæķĻèĤ²
    -0.08
    orny
    -0.08
    cts
    -0.08
    å¾Ģå¾Ģä¼ļ
    -0.08
    褥
    -0.08
    åİŁåĽłæĺ¯
    -0.08
    å¾Īéĩįè¦ģçļĦ
    -0.08
    POSITIVE LOGITS
    äºĨä¸Ģ份
    0.09
    ient
    0.09
    à¹Īà¸Ńà¸ĩ
    0.09
    äºĨä¸Ģ声
    0.09
    æ¦Ħ
    0.09
    ings
    0.09
    .shtml
    0.08
    ä¸Ģåı¥
    0.08
    ä¸Ģ份
    0.08
    ecast
    0.08
    Activations Density 0.003%

    No Known Activations