© 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. 34177
    Prev
    Next
    INDEX
    Explanations

    secondary, auxiliary, supplementary

    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
    èµĦ产管çIJĨ
    -0.09
    å¾Ĵ
    -0.09
    unas
    -0.08
    .removeFrom
    -0.08
    ubi
    -0.08
    æľºç¥¨
    -0.08
    åľ°ä¸ĭ
    -0.08
    é»ĺ
    -0.08
    é£İåIJ¹
    -0.08
    ä¸įåħģ许
    -0.08
    POSITIVE LOGITS
    次è¦ģ
    0.12
    åħµåĬĽ
    0.10
    è¾ħåĬ©
    0.10
    åī¯
    0.10
     secondary
    0.10
    åħµ
    0.10
     Secondary
    0.09
    èī²è°ĥ
    0.09
    secondary
    0.09
    Secondary
    0.09
    Activations Density 0.091%

    No Known Activations