© 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. 3462
    Prev
    Next
    INDEX
    Explanations

    cholesteryl ester transfer protein

    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
    è¾£
    -0.11
    ç¿»
    -0.10
    æĦıå¿Ĺ
    -0.10
    æ»Ĺ
    -0.09
    è·Łè¿Ľ
    -0.09
    严å¯Ĩ
    -0.09
    æ°´éĩı
    -0.09
    åħĭ
    -0.09
    丼æŀĹ
    -0.08
    æ°ĶåĬ¿
    -0.08
    POSITIVE LOGITS
    initializer
    0.09
    ICLE
    0.09
    gear
    0.08
     thừa
    0.08
    _CFG
    0.08
    _ACTIV
    0.08
    éĢĶå¾Ħ
    0.08
    çŁ³å®¶
    0.08
    lv
    0.08
    cfg
    0.08
    Activations Density 0.324%

    No Known Activations