© 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. 55002
    Prev
    Next
    INDEX
    Explanations

    US state and city abbreviations

    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
    æ´»ä¸ĭåİ»
    -0.08
    _ttl
    -0.08
    ä¸Ģç¬Ķ
    -0.08
     ali
    -0.08
    åľ¨å®¶
    -0.08
    inar
    -0.08
    æį¢ä¸ª
    -0.08
    è´Ń
    -0.07
    omen
    -0.07
    æĻı
    -0.07
    POSITIVE LOGITS
    æµĬ
    0.09
    ystack
    0.09
    ué
    0.09
    æĦıåij³
    0.09
    hee
    0.09
    åĪĨè¡Į
    0.09
    _DM
    0.08
    ä¿Ń
    0.08
     Paleo
    0.08
    éĴı
    0.08
    Activations Density 0.114%

    No Known Activations