© 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. 38435
    Prev
    Next
    INDEX
    Explanations

    abstract concepts or challenges

    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
    æľĢåŁºæľ¬
    -0.10
    åıĪ好
    -0.09
    éĤ£ç§į
    -0.09
    è¯ł
    -0.09
    éĤ£ä½į
    -0.09
     недо
    -0.08
    åĬ¨äºº
    -0.08
    让大家
    -0.08
    è¿Ļ家ä¼Ļ
    -0.08
    ä¹Łä¸įè¦ģ
    -0.08
    POSITIVE LOGITS
    idget
    0.10
    æľ¬èº«
    0.09
    OWL
    0.09
    ологии
    0.09
    pter
    0.09
    rocket
    0.08
    ny
    0.08
    rale
    0.08
    æĴ®
    0.08
    å±Ĥå±Ĥ
    0.08
    Activations Density 0.361%

    No Known Activations