© 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. 38511
    Prev
    Next
    INDEX
    Explanations

    7 and 8 followed by numbers or names

    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
    äºĽ
    -0.10
    åĴĮæĶ¯æĮģ
    -0.10
    æĪijå¾Ī
    -0.10
    ä¸ĢäºĽ
    -0.10
    _THAN
    -0.09
     sake
    -0.09
    æľīåĬ©
    -0.09
    æĪĴ
    -0.09
    è¾ĺ
    -0.09
     Ñĥзн
    -0.09
    POSITIVE LOGITS
    quier
    0.09
    etable
    0.09
    pered
    0.09
    лоÑĤ
    0.09
    rame
    0.09
    creen
    0.09
    ãģĿãģĨãģł
    0.09
    ters
    0.08
    rices
    0.08
    hear
    0.08
    Activations Density 0.182%

    No Known Activations