© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50559
    Prev
    Next
    INDEX
    Explanations

    servicing

    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
    æĶ¾å¤§
    -0.10
     temp
    -0.10
    ESCO
    -0.09
    =temp
    -0.09
    нак
    -0.09
    /temp
    -0.09
    ä¸į足
    -0.09
     Prescott
    -0.09
    EPS
    -0.09
    $temp
    -0.09
    POSITIVE LOGITS
     Dust
    0.12
    ç´§åĩij
    0.10
     dust
    0.09
    è¡£
    0.08
    åĢºæĿĥ
    0.08
    èĩªç§ģ
    0.08
    .Transactional
    0.08
    ogui
    0.08
    æĺİç¡®
    0.08
    æŁĦ
    0.08
    Activations Density 0.110%

    No Known Activations