© 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. 2910
    Prev
    Next
    INDEX
    Explanations

    e-mail actions

    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
    tring
    -0.10
    æĤĦ
    -0.09
    èĬ
    -0.09
    åĨĻä¸ĭ
    -0.09
    éĦĻ
    -0.09
    çIJĽ
    -0.08
    CHAN
    -0.08
    æģ¤
    -0.08
    adesh
    -0.08
    -Shirt
    -0.08
    POSITIVE LOGITS
    请大家
    0.12
    常çĶ¨
    0.09
    æĭ·
    0.09
     возд
    0.09
    ç§ijçłĶ
    0.09
    çģŃ
    0.08
    æŃ£å¸¸ä½¿çĶ¨
    0.08
     Sentence
    0.08
    丢äºĨ
    0.08
    grounds
    0.08
    Activations Density 0.034%

    No Known Activations