© 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. 63222
    Prev
    Next
    INDEX
    Explanations

    blur and blurry vision

    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
    ÙĪع
    -0.10
    lund
    -0.09
    ories
    -0.09
    auer
    -0.08
    空
    -0.08
    IALIZ
    -0.08
    urable
    -0.08
    eve
    -0.08
    .cloud
    -0.08
    çĦ¶æĺ¯
    -0.08
    POSITIVE LOGITS
    ingly
    0.11
    ä¸įæ¸ħ
    0.11
    çķĮå®ļ
    0.10
    è¨ĢãģĪãģ°
    0.09
    ignum
    0.09
    ulence
    0.09
    ç¿¡
    0.09
    ulent
    0.09
     Commons
    0.09
    涿
    0.09
    Activations Density 0.004%

    No Known Activations