© 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. 4403
    Prev
    Next
    INDEX
    Explanations

    recruitment agency employment

    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
    éĿ©æĸ°
    -0.10
    åĭĴ
    -0.09
    ä¼´
    -0.09
    çĶ·åŃ©åŃIJ
    -0.09
    ç§ī
    -0.09
    èµĽ
    -0.09
    ä»ĬçĶŁ
    -0.09
    èĩªåľ¨
    -0.09
    kke
    -0.08
    åħ¸
    -0.08
    POSITIVE LOGITS
    åĬ¡å·¥
    0.13
    çĶ¨å·¥
    0.13
    åĬ³åĬ¨åĬĽ
    0.10
    åĬ³åĬ¨èĢħ
    0.09
    éĿ¢
    0.09
    å²Ĺ
    0.09
    arf
    0.09
    arb
    0.09
    æīĵå·¥
    0.09
    åĬ³åĬ¡
    0.09
    Activations Density 0.114%

    No Known Activations