© 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. 11402
    Prev
    Next
    INDEX
    Explanations

    input device context

    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
    åIJĮè¡Į
    -0.10
    åħīçħ§
    -0.10
    æ»ĭåħ»
    -0.09
    ysize
    -0.09
    èĬ±å¼Ģ
    -0.09
    åªĽ
    -0.08
    é²ľèī³
    -0.08
     peers
    -0.08
    unsch
    -0.08
    Ñģол
    -0.08
    POSITIVE LOGITS
    çģµæķı
    0.10
    çģµ
    0.09
    çļĦåĬ¨ä½ľ
    0.09
    åĬ¨ä½ľ
    0.08
    Aliases
    0.08
    æı¡
    0.08
    å½ķåħ¥
    0.08
    ç»ĥä¹ł
    0.08
     Filed
    0.08
    Gesture
    0.08
    Activations Density 0.193%

    No Known Activations