© 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. 37767
    Prev
    Next
    INDEX
    Explanations

    `cliffe`, `Sullivan`, `Clement` surnames

    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
    æ¶Īè´¹åĵģ
    -0.11
    éĻ¨
    -0.10
    ä¸įåĬ¨
    -0.10
    IES
    -0.10
    æĬ½è±¡
    -0.10
    ç²Ł
    -0.09
    çĽĨåľ°
    -0.09
    erland
    -0.09
    èĤ¡
    -0.09
    çľĭçĶµå½±
    -0.09
    POSITIVE LOGITS
    åĽŁ
    0.09
    English
    0.09
    å®ľ
    0.09
    æĸ°è¥¿åħ°
    0.09
    _oct
    0.09
    澳洲
    0.08
     English
    0.08
    绵
    0.08
    伦æķ¦
    0.08
    æĮĤéĴ©
    0.08
    Activations Density 0.065%

    No Known Activations