© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19806
    Prev
    Next
    INDEX
    Explanations

    moisture vapor, entering, reflections

    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
    éģ®
    -0.09
    éľ²å¤©
    -0.09
    åĪĴ
    -0.08
    éľı
    -0.08
    /copyleft
    -0.08
     wastes
    -0.08
     Hust
    -0.08
    Friends
    -0.08
    æĺİç¡®è§Ħå®ļ
    -0.08
    éĿ¡
    -0.08
    POSITIVE LOGITS
    åģľæ»ŀ
    0.10
    èĵ¬
    0.09
    æĹħéĢĶ
    0.09
    æĹłèģĬ
    0.09
    使çĶ¨èĢħ
    0.09
    æĶ
    0.09
    _study
    0.09
    abad
    0.08
    æģĭ
    0.08
    èĬĹ
    0.08
    Activations Density 0.071%

    No Known Activations