© 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. 55240
    Prev
    Next
    INDEX
    Explanations

    about issues and matters

    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
    elpers
    -0.10
    èĦĨ
    -0.09
    urette
    -0.09
    éĻĨ
    -0.08
    ahan
    -0.08
    ä»ħä¾Ľ
    -0.08
    åĢĴ
    -0.08
    _LOOK
    -0.08
    éĢ
    -0.08
    mbH
    -0.08
    POSITIVE LOGITS
    ä¸Ģ个éĹ®é¢ĺ
    0.12
     elephant
    0.10
    æľĢåħ³éĶ®
    0.10
    æľĢéĩįè¦ģçļĦ
    0.10
    æijĨåľ¨
    0.10
    è¿Ļ个éĹ®é¢ĺ
    0.09
    æľĢéĩįè¦ģ
    0.09
    æ§Ľ
    0.09
     issue
    0.09
    è¿ĺæľīä¸Ģ个
    0.09
    Activations Density 0.042%

    No Known Activations