© 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. 7217
    Prev
    Next
    INDEX
    Explanations

    true or truly followed by qualifier

    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
    signal
    -0.09
    æ·³
    -0.09
    ses
    -0.09
    rete
    -0.09
    æĪĸèĢħåħ¶ä»ĸ
    -0.08
    atas
    -0.08
    lide
    -0.08
    xdc
    -0.08
    帧
    -0.08
     stamps
    -0.08
    POSITIVE LOGITS
    æĦıä¹īä¸ĬçļĦ
    0.18
    羣æŃ£çļĦ
    0.17
     truly
    0.16
    羣æŃ£
    0.16
    æĦıä¹īä¸Ĭ
    0.12
     genuinely
    0.12
    åĽ½éĻħåĮĸ
    0.11
    åĿļå®ŀçļĦ
    0.10
     Truly
    0.10
     true
    0.10
    Activations Density 0.026%

    No Known Activations