© 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. 35203
    Prev
    Next
    INDEX
    Explanations

    rates per unit/value

    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
    indre
    -0.09
    ç«łç¨ĭ
    -0.08
    æĹ¶ä»£çļĦ
    -0.08
    çĻ½äºij
    -0.08
    éĤµ
    -0.08
    æĸĹ
    -0.08
    æ²ī浸
    -0.08
    iani
    -0.08
    AFE
    -0.08
    å°¼åħĭ
    -0.07
    POSITIVE LOGITS
    ä¸ĩåĪĨ
    0.10
    äºīåĪĽ
    0.10
    çļĦåĬªåĬĽ
    0.10
    åŁºæķ°
    0.09
    Ads
    0.09
    æĬ½å¥ĸ
    0.09
    顾èĻij
    0.08
    è´»
    0.08
    çļĦå¿ĥçIJĨ
    0.08
    ãĤ»ãĥĥãĥĪ
    0.08
    Activations Density 0.061%

    No Known Activations