© 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. 21344
    Prev
    Next
    INDEX
    Explanations

    skinny or chubby descriptions

    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
    stones
    -0.09
    çĪ·
    -0.09
    	TokenName
    -0.09
     налиÑĩии
    -0.09
     sexes
    -0.09
    ÑĭÑĪ
    -0.09
    itre
    -0.09
    pora
    -0.08
    é¬ĵ
    -0.08
     dign
    -0.08
    POSITIVE LOGITS
    å··
    0.10
    est
    0.10
    ä¸ĬãģĴ
    0.09
    esor
    0.09
    ses
    0.09
    ish
    0.09
    okie
    0.09
    oze
    0.08
    ×Ķ
    0.08
    èĥį
    0.08
    Activations Density 0.001%

    No Known Activations