© 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. 5602
    Prev
    Next
    INDEX
    Explanations

    obtain a copy

    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
    é»į
    -0.09
    æį¡
    -0.09
    prov
    -0.09
    .precision
    -0.09
    pec
    -0.09
    ventus
    -0.08
    thought
    -0.08
    تÙĬ
    -0.08
    ľ
    -0.08
    éľĨ
    -0.08
    POSITIVE LOGITS
     инÑĦоÑĢмаÑĨии
    0.10
     rid
    0.10
     sucesso
    0.10
     Rid
    0.09
    arian
    0.09
    ech
    0.09
     gratuitement
    0.09
    ivor
    0.09
    fried
    0.09
    对èĩªå·±çļĦ
    0.09
    Activations Density 0.072%

    No Known Activations