© 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. 18191
    Prev
    Next
    INDEX
    Explanations

    states, president, vice president

    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
    lim
    -0.09
     Lim
    -0.09
    iring
    -0.09
    inue
    -0.08
    èĸ®
    -0.08
     lac
    -0.08
     aides
    -0.08
    æ¸łéģĵ
    -0.08
    UMENT
    -0.08
     lim
    -0.08
    POSITIVE LOGITS
    insky
    0.09
    plied
    0.09
    å®ģ
    0.08
    éĶ¡
    0.08
    çī¢åĽºæłijç«ĭ
    0.08
     Dispatch
    0.08
    åĩºåĽ½çķĻåѦ
    0.08
    踮
    0.08
    éħļ
    0.08
    ï¸ı
    0.08
    Activations Density 0.113%

    No Known Activations