© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 3118
    Prev
    Next
    INDEX
    Explanations

    LCD screens and displays

    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
    åĴĮåľ°åĮº
    -0.09
    sters
    -0.08
    arily
    -0.08
    稳妥
    -0.08
    fest
    -0.08
    /devices
    -0.08
    ittest
    -0.08
    ink
    -0.08
    ç¹ģæ®ĸ
    -0.08
    aries
    -0.08
    POSITIVE LOGITS
    ../../../
    0.12
    ingly
    0.10
    sWith
    0.10
    yat
    0.10
    ients
    0.09
    é¾ĻéŨ
    0.09
    .Accessible
    0.09
    å·¨æĺŁ
    0.09
    人人
    0.08
     пÑĢоÑģмоÑĤÑĢ
    0.08
    Activations Density 0.017%

    No Known Activations