© 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. 36132
    Prev
    Next
    INDEX
    Explanations

    states or provinces followed by administrative roles

    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
    ake
    -0.10
    æīĢåľ¨åľ°
    -0.09
     bum
    -0.09
    央è§Ĩ
    -0.09
    åŁĶ
    -0.09
    inds
    -0.09
    Msp
    -0.09
    ru
    -0.09
    acen
    -0.09
    åħļç»Ħ
    -0.09
    POSITIVE LOGITS
    è¿ĻçĤ¹
    0.09
    etty
    0.08
    blob
    0.08
    пиÑĤ
    0.08
    ä¹Łå¥½
    0.08
    è¿Ļä¸ĢçĤ¹
    0.08
    ç¦Ĭ
    0.08
    æľī害
    0.08
    Ùĩج
    0.08
    imb
    0.07
    Activations Density 0.309%

    No Known Activations