© 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. 23287
    Prev
    Next
    INDEX
    Explanations

    reputation and defamation

    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
    abler
    -0.09
    è¿Ŀ
    -0.09
     Ric
    -0.09
    æļ´é£İ
    -0.09
    æĵĴ
    -0.09
    èĥ½åĬĽå¼º
    -0.08
    scp
    -0.08
    强åĬ²
    -0.08
    ARING
    -0.08
    åĬłç´§
    -0.08
    POSITIVE LOGITS
    声èªī
    0.20
     reputation
    0.19
    åIJįèªī
    0.19
     reput
    0.16
    åIJį声
    0.15
     Reputation
    0.15
    ä¿¡èªī
    0.14
    åı£ç¢ij
    0.14
    åĵģçīĮ形象
    0.13
    æĬ¹
    0.12
    Activations Density 0.058%

    No Known Activations