© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21694
    Prev
    Next
    INDEX
    Explanations

    lease duration or years

    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
     Finance
    -0.09
    Finance
    -0.09
    éĽªå±±
    -0.09
    cam
    -0.09
    èĪģ
    -0.09
     ó
    -0.09
    edges
    -0.08
     finance
    -0.08
    åĬ©åѦ
    -0.08
    æıIJ款
    -0.08
    POSITIVE LOGITS
    ifetime
    0.09
    é£İæ°´
    0.09
    ç»Ī身
    0.09
    çģ«çĪĨ
    0.09
    å¹´éĻIJ
    0.09
    使çĶ¨æĿĥ
    0.09
     exhausting
    0.09
     exhaustion
    0.09
    ç´¯äºĨ
    0.09
    airy
    0.09
    Activations Density 0.054%

    No Known Activations