© 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. 11414
    Prev
    Next
    INDEX
    Explanations

    stay, leave, home, absent

    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
    èļĮ
    -0.09
    å¶Ĥ
    -0.08
    赦
    -0.08
     Stam
    -0.08
    æīĵæĭĽåij¼
    -0.08
    Styles
    -0.08
    éĽĨåĽ¢èĤ¡ä»½
    -0.08
    xFFFFFFFF
    -0.08
    ife
    -0.08
    è¾Ł
    -0.08
    POSITIVE LOGITS
    åģľçķĻåľ¨
    0.14
    çķĻåľ¨
    0.13
    åĽº
    0.10
     confines
    0.10
    ä½ı
    0.10
    _CTL
    0.10
    ãģĿãģĵãģ§
    0.10
    ç®ĹäºĨ
    0.10
    atak
    0.09
    åģľä¸ĭ
    0.09
    Activations Density 0.046%

    No Known Activations