© 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. 49483
    Prev
    Next
    INDEX
    Explanations

    power-related contexts

    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
    .onCreate
    -0.09
    ãģ«åIJijãģijãģ¦
    -0.08
    opus
    -0.08
    è´»
    -0.08
    éŁ¿
    -0.08
    çĶ°éĩİ
    -0.08
    页
    -0.08
    _saved
    -0.08
    iw
    -0.08
    ologia
    -0.08
    POSITIVE LOGITS
    缩水
    0.11
    åĽ¢
    0.10
    OWER
    0.09
    èĩªä¿¡
    0.09
    train
    0.09
    æĹ¶æ®µ
    0.09
    åįģ足
    0.08
    饮水
    0.08
    åľ°ä½į
    0.08
    åľ°æ¯¯
    0.08
    Activations Density 0.052%

    No Known Activations