© 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. 56390
    Prev
    Next
    INDEX
    Explanations

    payoff, rewards, benefits

    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
    çijķ
    -0.09
    æ¤įæłij
    -0.09
    çĽ¸äº²
    -0.09
    RetVal
    -0.09
    oter
    -0.09
    åIJ¸åıĸ
    -0.09
    ä¸Ģç»Ħ
    -0.09
    å¼Ģå¿ĥ
    -0.08
    æķ´é¡¿
    -0.08
    ogi
    -0.08
    POSITIVE LOGITS
    WATCH
    0.09
    女ç¥ŀ
    0.09
    iens
    0.09
     rewards
    0.09
    emet
    0.09
    Watch
    0.09
    ä¼ļæľī
    0.09
    tro
    0.08
    éĻĽä¸ĭ
    0.08
    驼
    0.08
    Activations Density 0.004%

    No Known Activations