© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52506
    Prev
    Next
    INDEX
    Explanations

    see what

    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
    åijĬ
    -0.08
    عت
    -0.08
    ecer
    -0.08
    æĹłæķ°æ¬¡
    -0.08
     ~
    -0.08
    绿水
    -0.08
    å±ķçİ°äºĨ
    -0.08
    argas
    -0.07
    itched
    -0.07
    Ñĥ
    -0.07
    POSITIVE LOGITS
    ä»ĸ们ä¼ļ
    0.13
    æĪIJè´¥
    0.11
    æ·ij
    0.10
    åĪ°åºķ
    0.10
    èµ°ä¸ĭåİ»
    0.10
    çīĴ
    0.10
    åIJ¬åIJ¬
    0.10
    éĻħ
    0.10
    æĽ´å¤ļ精彩
    0.10
    åİī害
    0.10
    Activations Density 0.039%

    No Known Activations