© 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. 30824
    Prev
    Next
    INDEX
    Explanations

    feel

    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
    æķĪèĥ½
    -0.09
    æľĢå¿«
    -0.08
    _LVL
    -0.08
    bes
    -0.08
    enta
    -0.08
    ically
    -0.08
    éĿ
    -0.08
    naire
    -0.08
    ady
    -0.08
    é¢ľèī²
    -0.08
    POSITIVE LOGITS
    æ°ijå¿ĥ
    0.10
    thing
    0.10
    åĦ¿
    0.10
    éļıå¤Ħ
    0.09
    åIJĦå¼Ĥ
    0.09
    èļĢ
    0.09
    è¿Ļè¾¹
    0.08
    å¥łåŁº
    0.08
    beit
    0.08
    ä»ĸä¼ļ
    0.08
    Activations Density 0.005%

    No Known Activations