© 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. 17038
    Prev
    Next
    INDEX
    Explanations

    freedom and flight

    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
    .toCharArray
    -0.10
    ä¸ĢæĿ¡é¾Ļ
    -0.09
    anka
    -0.09
    CharArray
    -0.08
    osi
    -0.08
    è´¤
    -0.08
    å¼Ī
    -0.08
    æ²¥
    -0.08
    oshi
    -0.08
    roids
    -0.08
    POSITIVE LOGITS
    èĩªçĶ±
    0.15
    èĩªåľ¨
    0.13
    çĻ½äºij
    0.12
    鸥
    0.12
    鸣类
    0.11
     freedom
    0.11
    é£ŀ
    0.10
    èĵĿ天
    0.10
    æ¯ĶæĪij
    0.10
    鸣
    0.10
    Activations Density 0.022%

    No Known Activations