© 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. 1060
    Prev
    Next
    INDEX
    Explanations

    issue, link, substance, condition

    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
    åIJį为
    -0.10
    éħ¬
    -0.09
    é¡·
    -0.08
    ignment
    -0.08
    ç¼Ĩ
    -0.08
    èĽĬ
    -0.08
     altern
    -0.08
    éĤ®æĶ¿
    -0.08
     sets
    -0.08
    两çĤ¹
    -0.08
    POSITIVE LOGITS
    è¦ģä¹Ī
    0.12
    either
    0.12
    æ¯Ķå¦Ĥ
    0.11
     either
    0.11
    诸å¦Ĥ
    0.11
    ither
    0.10
    æŁIJ个
    0.09
     algun
    0.09
    omething
    0.09
    جÙĪ
    0.09
    Activations Density 0.469%

    No Known Activations