© 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. 31189
    Prev
    Next
    INDEX
    Explanations

    US states and countries

    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
    æĪijæł¡
    -0.10
    æī£
    -0.10
    æŶéĹ´åĨħ
    -0.09
    è½½ä½ĵ
    -0.09
    /platform
    -0.09
    两家
    -0.09
    è¯¾æľ¬
    -0.08
    é²ľèī³
    -0.08
    对çŃĸ
    -0.08
    æıIJåīį
    -0.08
    POSITIVE LOGITS
     United
    0.09
    æ¾Ħæ¸ħ
    0.09
    åĬª
    0.08
     undisclosed
    0.08
    accent
    0.08
    _CTL
    0.08
    é¢ł
    0.08
    å¼ŁåŃIJ
    0.08
    Gar
    0.08
    çĸ«
    0.08
    Activations Density 0.050%

    No Known Activations