© 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. 50766
    Prev
    Next
    INDEX
    Explanations

    ohio court cases

    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
    åµĬ
    -0.12
    绵
    -0.11
    汨
    -0.10
    .instrument
    -0.10
     Noon
    -0.09
    ç»įåħ´
    -0.09
     Unicorn
    -0.09
    æµĻ
    -0.09
    æµĻæ±Łçľģ
    -0.09
    å¾Ģè¿Ķ
    -0.09
    POSITIVE LOGITS
     Ohio
    0.19
    Ohio
    0.18
     Cincinnati
    0.14
     ohio
    0.14
    éĤ¢åı°
    0.13
     Cleveland
    0.13
     Dayton
    0.12
    滹
    0.11
    è¡¡æ°´
    0.11
     Columbus
    0.11
    Activations Density 0.348%

    No Known Activations