© 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. 50830
    Prev
    Next
    INDEX
    Explanations

    file system operations

    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
    å¼ķ
    -0.10
    ä¸įçķĻ
    -0.09
    å¼ķãģį
    -0.09
     aster
    -0.08
    å©ļ纱
    -0.08
    urn
    -0.08
    ÙģÙĪر
    -0.08
    åįłé¢Ĩ
    -0.08
    ilian
    -0.08
    çĻ½éĽª
    -0.08
    POSITIVE LOGITS
    ä¼łåĩº
    0.10
    оÑĢо
    0.09
    ictim
    0.08
     printk
    0.08
    ç¦ıå¾·
    0.08
    pill
    0.08
    _##
    0.08
    ult
    0.08
    åĺ±
    0.08
    è´£ç¼ĸ
    0.08
    Activations Density 0.429%

    No Known Activations