© 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. 49931
    Prev
    Next
    INDEX
    Explanations

    school, church, cafeteria, hall, property

    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
    è¯ķéªĮåĮº
    -0.10
     Dad
    -0.09
    oded
    -0.09
    è¡£æŁľ
    -0.09
    ä¸īæľŁ
    -0.09
    æľīéĴ±
    -0.09
    åįİå°Ķè¡Ĺ
    -0.09
    è¯Ŀ说
    -0.09
    缴å±ŀ
    -0.09
    çĪ¸çĪ¸
    -0.09
    POSITIVE LOGITS
    åľºæīĢ
    0.12
    åł
    0.10
    åľºåľ°
    0.10
    ä¹ī
    0.09
    InBackground
    0.09
     school
    0.09
    uters
    0.09
    -pad
    0.08
     premises
    0.08
    /community
    0.08
    Activations Density 0.132%

    No Known Activations