© 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. 54015
    Prev
    Next
    INDEX
    Explanations

    polygon coordinates

    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
    黳
    -0.09
    _areas
    -0.09
    浸
    -0.09
    两款
    -0.09
    uggy
    -0.08
    çĥŁ
    -0.08
     Gad
    -0.08
    ByExample
    -0.08
    /Area
    -0.08
    actor
    -0.08
    POSITIVE LOGITS
    éĢĢ
    0.10
    çªģåĩº
    0.09
    ç¿ħèĨĢ
    0.09
    çĵ£
    0.09
    ç´§ç´§åĽ´ç»ķ
    0.09
    åıī
    0.09
    æīĵæĬĺ
    0.08
    ä¼´
    0.08
    èĻ¾
    0.08
    pike
    0.08
    Activations Density 0.131%

    No Known Activations