© 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. 53573
    Prev
    Next
    INDEX
    Explanations

    URL shorteners, file paths, media callsigns

    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
    è¿IJæ°Ķ
    -0.09
    еÑĩа
    -0.09
    å®ĪæĬ¤
    -0.09
    èĸ¤
    -0.09
     havoc
    -0.09
     ниÑĩ
    -0.09
    鬲
    -0.09
    éŨå¤ĸ
    -0.08
    éķ¬
    -0.08
    ungan
    -0.08
    POSITIVE LOGITS
    ä¸ĸ家
    0.09
     spit
    0.08
    ç¬Ķ
    0.08
    -lang
    0.08
    峡
    0.08
    aticon
    0.08
    åħ¨æĻ¯
    0.08
    èĵĵ
    0.08
     erect
    0.08
    èĻİ
    0.08
    Activations Density 0.003%

    No Known Activations