© 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. 33929
    Prev
    Next
    INDEX
    Explanations

    chinese characters or phrases

    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
    LIK
    -0.10
     благодаÑĢÑı
    -0.10
    embro
    -0.10
    ackers
    -0.09
     поÑı
    -0.09
    åIJĦæł·
    -0.09
    å¾Ĺ天çĭ¬åİļ
    -0.09
    ussen
    -0.09
     reasonably
    -0.09
    osg
    -0.09
    POSITIVE LOGITS
    æĪijè¿ĺæĺ¯
    0.10
    åıªèĥ½è¯´
    0.09
    å®ŀ践活åĬ¨
    0.09
    æīĢ以æĪij
    0.09
    æ¯ĽçĹħ
    0.09
    å¾Ĵ
    0.09
    没åħ³ç³»
    0.08
    档次
    0.08
    æºŁ
    0.08
    èĥİ
    0.08
    Activations Density 0.067%

    No Known Activations