© 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. 51186
    Prev
    Next
    INDEX
    Explanations

    elfinder, javascript, iMacros

    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
    CAST
    -0.09
     grand
    -0.09
    Gay
    -0.09
    å½ĵçĦ¶æĺ¯
    -0.08
    ÑģÑĤал
    -0.08
    æ©¡
    -0.08
    åĭĩ
    -0.08
    樨
    -0.08
    @m
    -0.08
    éĽĦ
    -0.08
    POSITIVE LOGITS
    scoped
    0.10
    èIJĿ
    0.09
     Dimit
    0.09
    ãi
    0.09
    BackingField
    0.08
     incon
    0.08
    CAPE
    0.08
    åħ¬å¯ĵ
    0.08
     leash
    0.08
    éļĻ
    0.08
    Activations Density 0.206%

    No Known Activations