© 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. 17369
    Prev
    Next
    INDEX
    Explanations

    the [noun]

    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
    以为
    -0.09
    说æ³ķ
    -0.08
    æŀ¶
    -0.08
    ito
    -0.08
    被称为
    -0.08
    éªħ
    -0.08
    nte
    -0.08
    дей
    -0.08
    责任å¿ĥ
    -0.08
    .acc
    -0.08
    POSITIVE LOGITS
    sembl
    0.11
    cert
    0.11
    ä¸Ģ项
    0.11
     opposed
    0.10
    ä¸Ģéĥ¨åĪĨ
    0.10
    åĪĩåħ¥çĤ¹
    0.10
    sembles
    0.10
    è¿ijäºĽ
    0.09
    ä¸ĢåĽ¢
    0.09
    InputDialog
    0.09
    Activations Density 0.048%

    No Known Activations