© 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. 19137
    Prev
    Next
    INDEX
    Explanations

    titles of books, albums, and memoirs

    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
     bat
    -0.10
    åģĥ
    -0.10
    åįıè°ĥåıijå±ķ
    -0.09
    .bat
    -0.09
    庸
    -0.08
    æĭĽèģĺä¿¡æģ¯
    -0.08
     Bat
    -0.08
    æĬĬæīĭ
    -0.08
    å¤įæŁ¥
    -0.08
     BAT
    -0.08
    POSITIVE LOGITS
    èĮ§
    0.09
    èł¹
    0.09
    è¿©
    0.09
    rise
    0.08
    ieres
    0.08
    误
    0.08
     Wong
    0.08
    urai
    0.08
    æĥ³ä¸įåĪ°
    0.08
    luck
    0.08
    Activations Density 0.199%

    No Known Activations