© 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. 18284
    Prev
    Next
    INDEX
    Explanations

    damage and its consequences

    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
    èĩ¾
    -0.13
    sWith
    -0.11
    MLE
    -0.11
    à¹Į
    -0.11
    ships
    -0.10
    ../../../
    -0.09
    UnderTest
    -0.09
    landers
    -0.09
    logan
    -0.09
    èĩ
    -0.09
    POSITIVE LOGITS
    crow
    0.10
    ogn
    0.09
    ëģĶ
    0.09
    çĶŁäº§æĢ»åĢ¼
    0.09
    æĦİ
    0.08
    -free
    0.08
    ÙĤ
    0.08
    Ñĩив
    0.08
    ments
    0.08
    _DESCRIPTOR
    0.08
    Activations Density 0.021%

    No Known Activations