© 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. 3841
    Prev
    Next
    INDEX
    Explanations

    family relationships

    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
    aro
    -0.09
    RTOS
    -0.09
    寥
    -0.09
     sıkıntı
    -0.08
    ROY
    -0.08
    OTO
    -0.08
     wonders
    -0.08
    TOOLS
    -0.08
    oto
    -0.08
    èĸĦå¼±
    -0.08
    POSITIVE LOGITS
    åİŁåħĪ
    0.10
    æĽ¾ä»»
    0.09
    æIJŃæ¡£
    0.09
    è·¨çķĮ
    0.09
    æĻĶ
    0.09
    çģ¿
    0.09
    lege
    0.09
    媳
    0.09
    ä»ĸæĽ¾
    0.09
    妻
    0.08
    Activations Density 0.077%

    No Known Activations