© 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. 56698
    Prev
    Next
    INDEX
    Explanations

    interest and incentive contexts

    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
    ç¿Ķ
    -0.09
    ä¸Ńå¤ĸ
    -0.09
    _specs
    -0.09
    è´«åĽ°
    -0.09
    è¿ĺä¸įå¤Ł
    -0.08
    赶
    -0.08
    /packages
    -0.08
    rics
    -0.08
    çĦķ
    -0.08
    è¿İæİ¥
    -0.08
    POSITIVE LOGITS
    åĪ©çĽĬ
    0.24
    çļĦåĪ©çĽĬ
    0.21
     interests
    0.16
     вÑĭгод
    0.14
    инÑĤеÑĢеÑģ
    0.13
     interest
    0.12
    åħ³å¿ĥ
    0.12
    åĪ©
    0.11
     stakes
    0.11
    interest
    0.11
    Activations Density 0.059%

    No Known Activations