© 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. 26584
    Prev
    Next
    INDEX
    Explanations

    cliché, taboo, generic

    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
    æѧ
    -0.09
    een
    -0.09
    èĭĹ
    -0.09
    夫
    -0.09
    å¡į
    -0.08
    åħ·ä½ĵæĥħåĨµ
    -0.08
    à¸ķรา
    -0.08
    craft
    -0.08
    ниÑĨÑĭ
    -0.08
    æݧ
    -0.08
    POSITIVE LOGITS
    0.11
    ety
    0.11
    è°Ľ
    0.10
    责任ç¼ĸè¾ij
    0.09
    å·²ä¹ħçļĦ
    0.09
    åģļæ³ķ
    0.09
    ichi
    0.09
    거리
    0.09
    è¿Ļ个æŶåĢĻ
    0.09
    renc
    0.09
    Activations Density 0.006%

    No Known Activations