© 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. 62565
    Prev
    Next
    INDEX
    Explanations

    suffix endings

    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
    åĴ±
    -0.09
    顾
    -0.09
     söz
    -0.09
    éķ¿çĽ¸
    -0.09
    twig
    -0.09
    ooo
    -0.09
    _FM
    -0.09
     LAP
    -0.09
     lap
    -0.09
    å¦Ļ
    -0.08
    POSITIVE LOGITS
    æĺŃ
    0.10
    lessly
    0.09
    atement
    0.09
    æİĪ
    0.09
    ading
    0.09
    pf
    0.09
    å°¾
    0.09
    apolis
    0.08
    è°·
    0.08
    gle
    0.08
    Activations Density 0.106%

    No Known Activations