© 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. 4327
    Prev
    Next
    INDEX
    Explanations

    harriers, flytrap, Kardon, Instinct

    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
    åĨ³å®ļ
    -0.09
    æ±ľ
    -0.09
    丹麦
    -0.09
    asti
    -0.09
    èĬĿåĬłåĵ¥
    -0.09
    åĽ½å®ī
    -0.08
    æĦĶ
    -0.08
    OTES
    -0.08
    奥æŀĹåĮ¹åħĭ
    -0.08
    NewProp
    -0.08
    POSITIVE LOGITS
    çĦ¶æĺ¯
    0.10
    åı¦æľī
    0.09
    祸
    0.09
     cele
    0.08
    éļľ
    0.08
    0.08
    doc
    0.08
    æĭ¢
    0.08
    åİŁ
    0.08
    âĢ
    0.08
    Activations Density 0.844%

    No Known Activations