© 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. 33783
    Prev
    Next
    INDEX
    Explanations

    "begged them" or "was in"

    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
    eri
    -0.09
     toll
    -0.09
    éļĶ
    -0.08
    å°¼æĸ¯
    -0.08
    PIP
    -0.08
    weit
    -0.08
     Toll
    -0.08
    éļĶ离
    -0.08
    å¹ķ
    -0.08
    åħ¨æ°ij
    -0.08
    POSITIVE LOGITS
    çŃĶåºĶ
    0.16
    å©ī
    0.14
    æİ¥åıĹäºĨ
    0.13
    æĭĴç»Ŀ
    0.13
    积æŀģåĵįåºĶ
    0.12
    说æĪij
    0.12
    åĵįåºĶ
    0.12
    çŃĶå¤į
    0.11
    åĽŀå¤į
    0.11
    äºİæĺ¯æĪij
    0.11
    Activations Density 0.111%

    No Known Activations