© 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. 38097
    Prev
    Next
    INDEX
    Explanations

    view followed by other words

    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
    管家
    -0.10
    gov
    -0.09
    adow
    -0.09
    PathComponent
    -0.08
    äºĴèģĶ
    -0.08
    ç¿Į
    -0.08
    åķ»
    -0.08
    ä¸İåħ¶
    -0.08
    ////////////////////////////////////////////////////////
    -0.08
    inem
    -0.08
    POSITIVE LOGITS
    =view
    0.10
    obel
    0.09
     ÑĩаÑģ
    0.09
    entic
    0.09
    seite
    0.09
    enie
    0.08
    èIJ¥
    0.08
     pics
    0.08
    ãĥ£
    0.08
    é£Ļ
    0.08
    Activations Density 0.019%

    No Known Activations