© 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. 49096
    Prev
    Next
    INDEX
    Explanations

    negotiate salary or fares

    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
    LastError
    -0.09
    _draft
    -0.09
     CONTRIBUTORS
    -0.08
    bro
    -0.08
    éĽı
    -0.08
    jer
    -0.08
     Announcement
    -0.08
    ç´łæĿIJ
    -0.08
     solitude
    -0.08
     Secrets
    -0.08
    POSITIVE LOGITS
    åįıåķĨ
    0.16
    çļĦçIJĨçĶ±
    0.15
    åķĨéĩı
    0.14
    æģ³
    0.13
    说æľį
    0.13
    çIJĨçĶ±
    0.13
    è°ĪåĪ¤
    0.12
     reasoning
    0.12
     negotiation
    0.11
    åĬĽäºī
    0.11
    Activations Density 0.042%

    No Known Activations