© 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. 59003
    Prev
    Next
    INDEX
    Explanations

    thing called [name]

    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
     thÆ°
    -0.08
    åı£æ°Ķ
    -0.08
    wards
    -0.08
    è¥Ł
    -0.08
    kaar
    -0.08
    à¤ł
    -0.08
    çľ¼çIJĥ
    -0.08
    Èĺ
    -0.08
    大æĸ¹
    -0.08
    ä¸Ģç³»åĪĹ
    -0.08
    POSITIVE LOGITS
    åı«åģļ
    0.12
    ä»Ģä¹Īåij¢
    0.10
    meld
    0.08
    åı«
    0.08
    åIJį为
    0.08
    OrElse
    0.08
    è°±
    0.08
    uren
    0.08
    æĪĸå¤ļ
    0.08
    å°ı康
    0.08
    Activations Density 0.030%

    No Known Activations