© 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. 53700
    Prev
    Next
    INDEX
    Explanations

    adaptation and adaptation

    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
    ified
    -0.11
    æ®Ĩ
    -0.10
    å½ĵä»Ĭ
    -0.09
    -eyed
    -0.09
    大èĩ£
    -0.09
    ÑīиÑĤ
    -0.08
    èĥ¡åIJĮ
    -0.08
    lish
    -0.08
    å¿ĥåºķ
    -0.08
    æģį
    -0.08
    POSITIVE LOGITS
    ively
    0.14
    quate
    0.11
    æĢ§å¼º
    0.10
    ewn
    0.10
    ions
    0.10
    æĢ§åĴĮ
    0.10
    ãĥ¬ãĥ¼ãĤ·ãĥ§ãĥ³
    0.10
    çĹĩ
    0.10
    cran
    0.10
    VERTISEMENT
    0.10
    Activations Density 0.027%

    No Known Activations