© 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. 51254
    Prev
    Next
    INDEX
    Explanations

    colors followed by nouns

    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
    éĻ²
    -0.09
    ifa
    -0.08
    åħ¨åĽ½äººæ°ij
    -0.08
    伫
    -0.08
    æŀģåħ¶
    -0.08
     cán
    -0.08
    nger
    -0.08
    zin
    -0.08
    enth
    -0.08
    éĶ¦ç»£
    -0.08
    POSITIVE LOGITS
    åĶ¤éĨĴ
    0.09
    PRETTY
    0.09
    .TODO
    0.09
    UEST
    0.08
    ä¸įæĺİçĻ½
    0.08
    æīĢæıIJä¾Ľ
    0.08
    æĩ
    0.08
    brook
    0.08
    åħĭæĭī
    0.08
    å±±
    0.08
    Activations Density 0.155%

    No Known Activations