© 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. 62189
    Prev
    Next
    INDEX
    Explanations

    more complex or successful outcomes

    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
    READING
    -0.10
    沧
    -0.09
    è¿ĻäºĽä¸ľè¥¿
    -0.09
    墨
    -0.09
    åİĿ
    -0.09
    ä¸įéĢļ
    -0.08
    æ¯ı次
    -0.08
    ãģ²ãģ¨
    -0.08
    ipo
    -0.08
    -library
    -0.08
    POSITIVE LOGITS
    çī¹åĪ«æĺ¯åľ¨
    0.08
    -volume
    0.08
    带ä¸Ĭ
    0.08
    èķĬ
    0.08
    æľĢéĩįè¦ģ
    0.08
    ãģĹãģĭãĤĤ
    0.08
    .NonNull
    0.08
    çºĤ
    0.08
    _CAST
    0.08
    .Style
    0.08
    Activations Density 0.192%

    No Known Activations