© 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. 22230
    Prev
    Next
    INDEX
    Explanations

    management and treatment considerations

    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
    éĿ
    -0.10
    éĻįèIJ½
    -0.10
    èĢIJçĶ¨
    -0.10
    æĬ½æŁ¥
    -0.09
    -cap
    -0.09
    atts
    -0.09
    ä¸Ģè§Ī
    -0.09
    ä¹ł
    -0.09
    åĸ»
    -0.08
    为广大
    -0.08
    POSITIVE LOGITS
    αι
    0.09
    æĹĭ
    0.09
    æijĦ
    0.08
     Sharma
    0.08
    ÑĢеÑĪ
    0.08
    rim
    0.08
    è¡Ķ
    0.08
    (DBG
    0.08
     treatment
    0.08
    hood
    0.08
    Activations Density 0.151%

    No Known Activations