© 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. 33259
    Prev
    Next
    INDEX
    Explanations

    numbers followed by time units

    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
    ï¸ı
    -0.16
    ../
    -0.11
    ä¸Ģå¤Ħ
    -0.09
    tracted
    -0.09
    -0.09
    ÑĢаÑģ
    -0.09
    wards
    -0.08
    amp
    -0.08
    	TokenName
    -0.08
    们
    -0.08
    POSITIVE LOGITS
    teenth
    0.12
    жд
    0.12
    -thirds
    0.12
    -dimensional
    0.11
    fold
    0.11
     hundred
    0.10
    eenth
    0.10
    -third
    0.09
    ç¼¥
    0.09
    -five
    0.09
    Activations Density 0.259%

    No Known Activations