© 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. 1931
    Prev
    Next
    INDEX
    Explanations

    car models and sales

    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
    èĭį
    -0.08
    æ¸İ
    -0.08
    åħ±çĶŁ
    -0.08
     помеÑī
    -0.08
    çī¹ä»·
    -0.08
    移éĢģ
    -0.07
    é¢ĦåĪ¶
    -0.07
    ä¾Ľæ°´
    -0.07
    æī§ä¸ļ
    -0.07
    èĴľ
    -0.07
    POSITIVE LOGITS
    车åŀĭ
    0.15
    车主
    0.15
    æĸ°è½¦
    0.15
    驾驶
    0.15
    车身
    0.14
    è´Ń车
    0.14
    åĨħ饰
    0.14
    è¿Ļ款车
    0.13
    车è¾Ĩ
    0.13
     car
    0.13
    Activations Density 0.583%

    No Known Activations