© 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. 56057
    Prev
    Next
    INDEX
    Explanations

    remake, reboot, reimplementation, reissue

    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
    æĥĿ
    -0.09
    kir
    -0.09
    .assertj
    -0.08
     Rogue
    -0.08
     Mo
    -0.08
    gmt
    -0.08
    chter
    -0.08
    ãģķãģĪ
    -0.07
    èĢIJå¿ĥ
    -0.07
    baugh
    -0.07
    POSITIVE LOGITS
    èĤ¤
    0.10
    imations
    0.10
    ÙĬÙĩ
    0.10
    鸷
    0.09
    èijŃ
    0.09
    ä¹ĭä½ľ
    0.09
    å¿Į
    0.09
    æĥ³æĥ³
    0.09
    éĹªçĶµ
    0.09
    åıįä¹ĭ
    0.09
    Activations Density 0.040%

    No Known Activations