© 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. 58804
    Prev
    Next
    INDEX
    Explanations

    financial gain benefit

    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
     Watson
    -0.08
    ception
    -0.08
    墨西åĵ¥
    -0.08
    çĤĬ
    -0.07
    æĦıåIJij
    -0.07
    åĮĪ奴
    -0.07
    sic
    -0.07
    _LS
    -0.07
    ç¾İæ´²
    -0.07
    èIJ¥è¿IJ
    -0.07
    POSITIVE LOGITS
    好å¤Ħ
    0.14
    åĪ©çĽĬ
    0.13
    çīŁ
    0.12
    çļĦ好å¤Ħ
    0.11
    åĽŀæĬ¥
    0.10
    æīĢå¾Ĺ
    0.10
     benefit
    0.10
     gain
    0.10
    gain
    0.10
    订è´Ń
    0.10
    Activations Density 0.203%

    No Known Activations