© 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. 5494
    Prev
    Next
    INDEX
    Explanations

    asking how to

    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
    olest
    -0.10
    uble
    -0.09
    渡
    -0.09
    iens
    -0.09
    pected
    -0.09
    slashes
    -0.09
    esting
    -0.08
    ,ID
    -0.08
    UBLE
    -0.08
    羸
    -0.08
    POSITIVE LOGITS
    ä¹Łç®Ĺ
    0.11
    æ¸ļ
    0.09
    ä¸įç®Ĺ
    0.09
    ä¹°ä¸ľè¥¿
    0.08
    ban
    0.08
    樾
    0.08
    åĮºåĪ«
    0.08
    å²·
    0.08
     Ban
    0.08
    çĶ«
    0.08
    Activations Density 0.027%

    No Known Activations