© 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. 48028
    Prev
    Next
    INDEX
    Explanations

    test suite integration

    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°¸ä¹ħ
    -0.10
    使çĶ¨èĢħæĪĸ
    -0.10
    ведениÑı
    -0.09
    ling
    -0.09
    å°¾
    -0.09
    è°ĭæ±Ĥ
    -0.09
    _ble
    -0.09
     Thorn
    -0.09
    使çĶ¨èĢħ
    -0.09
    å§Ĭ
    -0.09
    POSITIVE LOGITS
    æµĭè¯ķ
    0.12
     tests
    0.12
     testing
    0.11
    arness
    0.11
     Tests
    0.11
     ÑĤеÑģÑĤ
    0.10
    Testing
    0.10
     test
    0.09
    /tests
    0.09
     written
    0.09
    Activations Density 0.320%

    No Known Activations