© 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. 48541
    Prev
    Next
    INDEX
    Explanations

    names and greetings

    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
     themselves
    -0.10
    横
    -0.09
    æľ¬èº«çļĦ
    -0.09
    æ©«
    -0.09
     Phill
    -0.08
     pro
    -0.08
    ç²
    -0.08
    зеÑĢ
    -0.08
    åįİåĮĹ
    -0.08
    èĢģèĻİæľº
    -0.08
    POSITIVE LOGITS
    ä½łæĺ¯
    0.10
    æī©åħħ
    0.09
    èµĦ
    0.09
    å«Ĥ
    0.09
    åıĶåıĶ
    0.09
    Ħ件
    0.09
    ä½łè¿ĺ
    0.09
    éĴ®
    0.08
    alg
    0.08
    侬
    0.08
    Activations Density 0.052%

    No Known Activations