© 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. 34152
    Prev
    Next
    INDEX
    Explanations

    want to/like to/think about

    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
    IRON
    -0.08
    ç´¯äºĨ
    -0.08
    /includes
    -0.08
    人éĥ½
    -0.08
    åĽ°
    -0.08
     شأÙĨ
    -0.08
    uib
    -0.08
    MOST
    -0.08
    åĺ´
    -0.08
     outs
    -0.08
    POSITIVE LOGITS
    äº¤æĽ¿
    0.09
    æĪijåıĪ
    0.09
    éĤ£ä½į
    0.09
    _refl
    0.09
    å°½æĹ©
    0.09
    dbc
    0.09
    ä¸ĭä¸Ģ代
    0.09
    зон
    0.09
    нее
    0.08
    å¿Ĩ
    0.08
    Activations Density 0.038%

    No Known Activations