© 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. 17481
    Prev
    Next
    INDEX
    Explanations

    civil liberties, rights, society, war, laws, emergencies, aviation

    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
    豺
    -0.10
     Carey
    -0.10
    ober
    -0.10
    (Intent
    -0.09
     Fargo
    -0.09
    BIN
    -0.09
    AMA
    -0.09
    æĶ¹
    -0.08
    çļĩ
    -0.08
    UrlParser
    -0.08
    POSITIVE LOGITS
    usk
    0.09
    -minded
    0.09
    ç´łåħ»
    0.09
    izational
    0.09
    itas
    0.09
    ilan
    0.08
    饬
    0.08
    تس
    0.08
    æĭ¥æĬ¤
    0.08
    ikan
    0.08
    Activations Density 0.039%

    No Known Activations