© 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. 34370
    Prev
    Next
    INDEX
    Explanations

    physical objects and tools

    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
    è¿ŀéĶģ
    -0.10
    agma
    -0.09
     завод
    -0.09
    èĽĢ
    -0.08
    åĸ·
    -0.08
    è¿¥
    -0.08
    声åĵį
    -0.08
    æ³½
    -0.08
     verm
    -0.08
    ondon
    -0.08
    POSITIVE LOGITS
    津贴
    0.09
    æĹłæĥħ
    0.09
    ç¢Ĺ
    0.09
    éĴµ
    0.09
    æ¶ĤæĬ¹
    0.08
    deg
    0.08
    ä»ĬçĶŁ
    0.08
    è¿ij
    0.08
    æĵĢ
    0.08
    海滨
    0.08
    Activations Density 0.054%

    No Known Activations