© 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. 52546
    Prev
    Next
    INDEX
    Explanations

    deoxyadenosine

    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
    etty
    -0.10
    åŁİ乡
    -0.10
    è¡Įç¨ĭ
    -0.09
    对æİ¥
    -0.09
    åĬ¨éĿĻ
    -0.09
    å§ij
    -0.09
    combe
    -0.09
    ics
    -0.09
    raq
    -0.09
    欧å¼ı
    -0.09
    POSITIVE LOGITS
    æIJĤ
    0.10
    æµģéĢļ
    0.09
     Plaza
    0.09
    ç¡Ĵ
    0.09
     Rid
    0.09
     opportun
    0.08
    eron
    0.08
    æĤłæĤł
    0.08
    æī£
    0.08
    ¿
    0.08
    Activations Density 0.107%

    No Known Activations