© 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. 32527
    Prev
    Next
    INDEX
    Explanations

    visible signs or defects

    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
    åıijçİ°èĩªå·±
    -0.10
    orca
    -0.09
    isman
    -0.09
    inals
    -0.09
    rim
    -0.09
     Ñģвоим
    -0.09
    à¹ģà¸Ĺ
    -0.09
    ÑĢин
    -0.09
    åĴĮåľ°åĮº
    -0.09
     Rifle
    -0.08
    POSITIVE LOGITS
    踪
    0.10
    ç¼Ĺ
    0.10
    éĻIJãĤĬ
    0.10
    æ·¦
    0.09
    ATOR
    0.09
    nore
    0.09
    izable
    0.09
    isable
    0.09
    elman
    0.08
    æĻ°
    0.08
    Activations Density 0.031%

    No Known Activations