© 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. 50022
    Prev
    Next
    INDEX
    Explanations

    Welcomes, Halts, Enhances, copes, Buys, Announces

    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
    ç½
    -0.10
    åĨįåİ»
    -0.09
    _PWR
    -0.09
    èĢĮåİ»
    -0.09
    æĿĵ
    -0.09
    å¬ī
    -0.08
    ibu
    -0.08
    漪
    -0.08
    ariat
    -0.08
    éļıåį³
    -0.08
    POSITIVE LOGITS
    为ä¸Ģä½ĵ
    0.10
    kea
    0.10
    irá
    0.09
    äºĨ许å¤ļ
    0.09
    äºĨå¤ļå°ij
    0.09
    -Nov
    0.09
    æ¹Ľ
    0.09
    对æİ¥
    0.08
    elijk
    0.08
    èĹıçĿĢ
    0.08
    Activations Density 0.312%

    No Known Activations