© 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. 30949
    Prev
    Next
    INDEX
    Explanations

    Sussex Brighton Palace

    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
     Texas
    -0.13
    å¾·å·ŀ
    -0.12
    Texas
    -0.12
     Houston
    -0.11
    æ¼³
    -0.10
     Texans
    -0.10
     TEX
    -0.10
     Arabia
    -0.09
    .persist
    -0.09
    ç¦ıå·ŀ
    -0.09
    POSITIVE LOGITS
    èĵŁ
    0.10
     Canter
    0.10
     Brighton
    0.09
    anine
    0.09
    诸èijĽ
    0.09
     CActive
    0.09
    èĩªç§ģ
    0.09
    رÙĪÙģ
    0.09
     Sussex
    0.08
    妲
    0.08
    Activations Density 0.168%

    No Known Activations