© 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. 31535
    Prev
    Next
    INDEX
    Explanations

    cheeky British

    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
    å¨ģåIJį
    -0.11
    æĩĭ
    -0.10
    ngine
    -0.10
    tein
    -0.09
    ä¸įèµ·
    -0.09
    éĻį温
    -0.09
    sti
    -0.09
    çĦ¶æĺ¯
    -0.09
    hus
    -0.09
    强åĬĽ
    -0.08
    POSITIVE LOGITS
    åįģ足
    0.09
    aroo
    0.09
    åįĸ
    0.08
    bones
    0.08
    ERC
    0.08
    zelf
    0.08
    CTX
    0.08
    amp
    0.08
    ier
    0.08
    èµĬ
    0.08
    Activations Density 0.004%

    No Known Activations