© 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. 19346
    Prev
    Next
    INDEX
    Explanations

    toads and frogs

    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
    绶
    -0.09
    åīª
    -0.09
    æĹĹå¸ľ
    -0.09
    LAS
    -0.09
    alto
    -0.08
    éĥ½çŁ¥éģĵ
    -0.08
    赶
    -0.08
    éĩį建
    -0.08
    èĪĶ
    -0.08
     ted
    -0.08
    POSITIVE LOGITS
    æ¦Ľ
    0.11
    åľŁåľ°
    0.09
    麻
    0.08
    å°ıåŃIJ
    0.08
    æ°¸è¿ľä¸įä¼ļ
    0.08
    amus
    0.08
    æ¥Ķ
    0.08
    DBG
    0.08
    åĬŁ
    0.08
    emma
    0.08
    Activations Density 0.084%

    No Known Activations