© 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. 2166
    Prev
    Next
    INDEX
    Explanations

    utah/ica ending context

    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
    ordin
    -0.09
    临港
    -0.08
    ally
    -0.08
    ordinates
    -0.08
    è´¢
    -0.08
    roud
    -0.08
    大å®ĹåķĨåĵģ
    -0.08
    è¢ĭ
    -0.08
    -budget
    -0.08
    常å§Ķ
    -0.08
    POSITIVE LOGITS
    éĿŀåĩ¡
    0.09
    gregate
    0.08
    åĺ´
    0.08
    tré
    0.08
    佬
    0.08
    ester
    0.08
    æĬ¹
    0.08
    ium
    0.08
    讽
    0.08
     vs
    0.08
    Activations Density 0.001%

    No Known Activations