© 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. 11075
    Prev
    Next
    INDEX
    Explanations

    measuring ingredients and quantities

    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
    Ä©nh
    -0.09
    ipel
    -0.09
    éģĹæĨ¾
    -0.08
    æĥłæ°ij
    -0.08
    åij¨å¹´
    -0.08
     bron
    -0.08
    æĻ®
    -0.08
    驾
    -0.08
    èŁł
    -0.08
    éĸ±
    -0.07
    POSITIVE LOGITS
    çĴ©
    0.11
    å·®ä¸įå¤ļ
    0.10
    fork
    0.09
    ëŁī
    0.09
    æ¾Ħæ¸ħ
    0.09
    Ñģо
    0.09
    大约
    0.08
    丽
    0.08
    éĩįéĩı
    0.08
    BOUND
    0.08
    Activations Density 0.010%

    No Known Activations