© 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. 21496
    Prev
    Next
    INDEX
    Explanations

    chatting or speaking with others

    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
    路段
    -0.09
    obel
    -0.09
    æ³ķåĪ¶
    -0.08
    spot
    -0.08
    梧
    -0.08
    éĹª
    -0.08
     пиÑĤ
    -0.08
     Clarkson
    -0.08
    hand
    -0.08
     spaghetti
    -0.07
    POSITIVE LOGITS
    ój
    0.12
    ä¹ħäºĨ
    0.09
    annon
    0.09
     Grim
    0.09
    /contact
    0.09
    è°Ī
    0.09
    APPER
    0.09
    ä¿©
    0.09
     Carpenter
    0.09
    èģĬ
    0.09
    Activations Density 0.056%

    No Known Activations