© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52663
    Prev
    Next
    INDEX
    Explanations

    FOR Release enquiries MEDIA

    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
    åIJĪæł¼
    -0.10
    é¦Ĩ
    -0.09
    ä¼ĺ
    -0.09
    è´´åIJ§
    -0.09
    Programming
    -0.08
    programming
    -0.08
    èĢģåħ¬
    -0.08
    ikel
    -0.08
    çĶŁåŃĺ
    -0.08
    Slots
    -0.08
    POSITIVE LOGITS
     Claw
    0.09
    第ä¸ĢæŶéĹ´
    0.09
    æĹłå£°
    0.09
    身å¿ĥåģ¥åº·
    0.09
    æݥ触åĪ°
    0.09
    森
    0.09
    ä¸Ģå¤ľ
    0.08
    rito
    0.08
    ipp
    0.08
    éĢ¢
    0.08
    Activations Density 0.023%

    No Known Activations