© 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. 53956
    Prev
    Next
    INDEX
    Explanations

    vinyl flooring

    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
     barg
    -0.09
    CBS
    -0.08
     Mex
    -0.08
    å¥ī
    -0.08
    oru
    -0.08
     Levy
    -0.08
    ðŁı»
    -0.08
    mers
    -0.08
    çļ¿
    -0.08
    ä¸įå®ī
    -0.07
    POSITIVE LOGITS
    à¸Ķา
    0.10
    å¹Ħ
    0.10
    ัà¸ģษ
    0.10
    磾
    0.10
    åİļåİļ
    0.09
    çĿ«æ¯Ľ
    0.09
    çĺ¸
    0.09
    uffs
    0.09
    åĸı
    0.09
    بÙĪ
    0.09
    Activations Density 0.007%

    No Known Activations