© 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. 21854
    Prev
    Next
    INDEX
    Explanations

    how, what, why questions

    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
    禧
    -0.09
    溷
    -0.09
    æ«ĥ
    -0.08
    sure
    -0.08
    精彩çļĦ
    -0.08
    è¦ģä¹Ī
    -0.08
    家åħ¬åı¸
    -0.08
    .utilities
    -0.07
    ola
    -0.07
    èµ°å»Ĭ
    -0.07
    POSITIVE LOGITS
    lip
    0.10
    çľĭè§ģ
    0.09
    soever
    0.09
    åIJ¬è§ģ
    0.09
     ÑģÑĤепени
    0.09
    abouts
    0.08
    人éĢł
    0.08
    æĪį
    0.08
    Inside
    0.08
    inside
    0.08
    Activations Density 0.111%

    No Known Activations