© 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. 10536
    Prev
    Next
    INDEX
    Explanations

    out of

    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
    éĿ¢åīį
    -0.08
    å¿ĥ缮ä¸Ń
    -0.08
    pped
    -0.08
    åĪĴ
    -0.08
    spl
    -0.08
    æ¥ŀ
    -0.08
    æĿ¥è®²
    -0.07
    æĺĶ
    -0.07
    aces
    -0.07
    åĽŀåİ»
    -0.07
    POSITIVE LOGITS
    ær
    0.10
    ture
    0.10
    æĺĩ
    0.09
    gradable
    0.09
    å°ijæķ°
    0.09
    éĢł
    0.09
    otify
    0.09
    /out
    0.09
    bound
    0.09
    tain
    0.09
    Activations Density 0.016%

    No Known Activations