© 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. 53070
    Prev
    Next
    INDEX
    Explanations

    ball pass and touch

    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
    åĭ
    -0.10
    æĭ±
    -0.09
    æĬķèµĦåŁºéĩij
    -0.09
    coat
    -0.09
    bucks
    -0.08
    èµĺ
    -0.08
    åħ¼èģĮ
    -0.08
    пÑĢом
    -0.08
    è´¢åĬĽ
    -0.08
    ç¦Ģ
    -0.08
    POSITIVE LOGITS
    çģµåĬ¨
    0.09
    æĿ²
    0.09
    éŀĭ
    0.09
    浪潮
    0.09
    egin
    0.08
    upe
    0.08
     \`
    0.08
    etty
    0.08
    atrice
    0.08
     à¹Ĩ
    0.08
    Activations Density 0.008%

    No Known Activations