© 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. 57570
    Prev
    Next
    INDEX
    Explanations

    lists of items separated by commas

    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
    éļ¾è¿ĩ
    -0.09
    深交
    -0.09
    ivia
    -0.08
    亲å¯Ĩ
    -0.08
    .↵↵
    -0.08
    åħ´èĩ´
    -0.08
    ä»Ģä¹Īæł·
    -0.08
    ippy
    -0.08
    EEK
    -0.07
    _NB
    -0.07
    POSITIVE LOGITS
     {}.
    0.12
    ãĢĤ
    0.10
    “.
    0.09
    æĤ¬
    0.08
    пÑĥ
    0.08
    å°¹
    0.08
    åĪĿä¸ī
    0.08
     pound
    0.08
     ().
    0.08
    åĶ¿
    0.07
    Activations Density 0.953%

    No Known Activations