© 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. 61320
    Prev
    Next
    INDEX
    Explanations

    models, variants, versions

    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
    好好
    -0.09
    å°½éĩı
    -0.09
    第ä¸Ģä½į
    -0.09
    大çīĩ
    -0.08
    åħ«å¤§
    -0.08
    é¼ĵåĬ±
    -0.08
    ä¹ĭåŁİ
    -0.08
    çĸı
    -0.08
    2
    -0.08
    6
    -0.08
    POSITIVE LOGITS
    åŀĭåı·
    0.12
     variants
    0.11
     sibling
    0.10
     variations
    0.09
     variant
    0.09
    unga
    0.09
    ë³Ģ
    0.09
    æľºåŀĭ
    0.09
    å¤Ń
    0.09
     variation
    0.09
    Activations Density 0.125%

    No Known Activations