© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9400
    Prev
    Next
    INDEX
    Explanations

    Mayo Clinic, Costco size

    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
    çĪ·
    -0.10
    è¿Ĥ
    -0.09
    æĥ³åĬŀæ³ķ
    -0.09
    çĦ¶æĺ¯
    -0.09
    ä¾®
    -0.09
    éŃģ
    -0.09
    éĻ¤å¤ķ
    -0.09
     возможноÑģÑĤи
    -0.09
    liness
    -0.09
    ROID
    -0.09
    POSITIVE LOGITS
    ëį°
    0.10
    è´¨åľ°
    0.09
    aurus
    0.08
    åĮºåĪĨ
    0.08
    åĮºåĪ«
    0.08
    åħ´è¶£
    0.08
     ups
    0.08
    Transpose
    0.08
    stro
    0.08
    eros
    0.08
    Activations Density 0.004%

    No Known Activations