© 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. 50373
    Prev
    Next
    INDEX
    Explanations

    accentuate or enhance

    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
    รà¸ģ
    -0.11
    幡
    -0.10
    plates
    -0.09
    _CONSTANT
    -0.09
    isma
    -0.09
    âĢ¾
    -0.09
    'icon
    -0.09
    houses
    -0.09
    çĥŃè¡Ģ
    -0.09
    аÑģÑģ
    -0.09
    POSITIVE LOGITS
    uate
    0.13
    uating
    0.10
    æŁIJä¸Ģ
    0.10
    æīĵ好
    0.09
    uates
    0.09
    åİŁæľī
    0.08
    è¿Ļ个è¡Įä¸ļ
    0.08
    éĻµ
    0.08
    rn
    0.08
    oma
    0.08
    Activations Density 0.010%

    No Known Activations