© 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. 49624
    Prev
    Next
    INDEX
    Explanations

    summer session, reading, weekend, temperatures, holiday

    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
    åĨĻçĿĢ
    -0.11
    GPL
    -0.09
    uintptr
    -0.09
    ees
    -0.09
    eff
    -0.09
     Garland
    -0.09
    èĮĿ
    -0.09
    finder
    -0.09
    esus
    -0.08
    .Dataset
    -0.08
    POSITIVE LOGITS
    steller
    0.09
    çĶ¨éĩı
    0.09
    oron
    0.09
    ÑĤе
    0.09
    é¹ĸ
    0.09
    ouch
    0.08
    thon
    0.08
    èĮ¬
    0.08
    æĭ¼
    0.08
     scoop
    0.08
    Activations Density 0.035%

    No Known Activations