© 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. 22305
    Prev
    Next
    INDEX
    Explanations

    hidden things and secrets

    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
    èĢIJ
    -0.09
    ç¥Ģ
    -0.09
    akh
    -0.09
    æĦŁäºº
    -0.08
    ç¡ħè°·
    -0.08
    è¦ģæĥ³
    -0.08
     curb
    -0.08
    åł¡
    -0.08
    æIJĤ
    -0.08
    å¿įåıĹ
    -0.08
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.12
    驺
    0.11
    æºľ
    0.10
    ÑģÑĭл
    0.10
    pire
    0.10
    以åħį
    0.09
    ç§ģèĩª
    0.09
    以éĺ²
    0.09
    éĩijæ²Ļ
    0.09
    ä¸Ŀ毫
    0.09
    Activations Density 0.033%

    No Known Activations