© 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. 55131
    Prev
    Next
    INDEX
    Explanations

    flower, vase, bar, candle, glass

    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
    äºĶæĺŁ
    -0.11
    .wall
    -0.09
    ç«Ļéķ¿
    -0.09
    åħ¬çĽĬæĢ§
    -0.09
    ajs
    -0.09
    ä¿Ŀåħ»
    -0.08
    ä¼ļ对
    -0.08
    积æ·Ģ
    -0.08
    çĶ¨åľ°
    -0.08
    å£ģ纸
    -0.08
    POSITIVE LOGITS
    åĿį
    0.10
    çĽħ
    0.09
    _gpu
    0.09
    åħ·
    0.09
    ÑĩÑĮ
    0.09
    éĴŁ
    0.08
    éķ«
    0.08
     stom
    0.08
    幸
    0.08
     tou
    0.08
    Activations Density 0.078%

    No Known Activations