© 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. 51376
    Prev
    Next
    INDEX
    Explanations

    self-assembly

    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
    çĦļ
    -0.10
    èĥ½çľĭåĩº
    -0.09
    .addTo
    -0.09
     Cook
    -0.09
    åĢ¾åIJ¬
    -0.08
    пеÑĢед
    -0.08
    _CT
    -0.08
    ç§ij
    -0.08
    ICO
    -0.08
    Iter
    -0.08
    POSITIVE LOGITS
    ä¼ij
    0.10
    第ä¸ĢæŃ¥
    0.09
    æľīåºı
    0.09
    æݧåĪ¶
    0.08
    uc
    0.08
    Stroke
    0.08
    stell
    0.08
    angi
    0.08
    æݧ
    0.08
    建çŃijå¸Ī
    0.08
    Activations Density 0.659%

    No Known Activations