© 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. 19572
    Prev
    Next
    INDEX
    Explanations

    athymic, athlete, Atherton, Athens

    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
    æ±ģ
    -0.09
    ions
    -0.09
    ij
    -0.09
    noinspection
    -0.09
    åľºéĿ¢
    -0.09
    irs
    -0.09
    è´½
    -0.08
    ç½²
    -0.08
    æľķ
    -0.08
    ample
    -0.08
    POSITIVE LOGITS
    çĦ¶æĺ¯
    0.12
    ypical
    0.10
    è£ħå¤ĩåĪ¶éĢł
    0.10
    atype
    0.09
    soever
    0.09
    bé
    0.09
    acus
    0.09
    æĺİçŁ¥
    0.09
    links
    0.09
    maal
    0.09
    Activations Density 0.026%

    No Known Activations