© 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. 32007
    Prev
    Next
    INDEX
    Explanations

    car models

    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
    icers
    -0.09
    åºĦ严
    -0.09
     вÑģÑı
    -0.09
    èĩªå·±
    -0.08
    leet
    -0.08
    led
    -0.08
     Woj
    -0.08
    ceptors
    -0.08
    å¸Ŀ
    -0.08
    å·¨
    -0.08
    POSITIVE LOGITS
    å¾ģæ±Ĥ
    0.10
    çĶ·å¥³
    0.10
    åĩºçĤī
    0.09
    åĩĨåħ¥
    0.09
    顾
    0.09
     ÃŃch
    0.09
    åĽĽæĸ¹
    0.09
     fil
    0.09
    eful
    0.09
    身亡
    0.09
    Activations Density 0.018%

    No Known Activations