© 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. 39243
    Prev
    Next
    INDEX
    Explanations

    sock monkeys, Lionel, dollhouse, Little Pony

    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
    票æĪ¿
    -0.10
    æĸ°éĹ»ä¸Ńå¿ĥ
    -0.09
    èĻ¬
    -0.09
    æĥ«
    -0.09
    åĬ¾
    -0.09
    èĩªåªĴä½ĵ
    -0.09
    ä¸įæĩĪ
    -0.08
    æĶ
    -0.08
    æĥ¬æĦı
    -0.08
    ç²¾è£ħ
    -0.08
    POSITIVE LOGITS
    æĺ¾
    0.09
    éĵ²
    0.09
     wishes
    0.08
    Redirect
    0.08
    Meal
    0.08
    é¦ĸæī¹
    0.08
     hol
    0.08
    åĵģ
    0.08
     labour
    0.08
    éķ°
    0.08
    Activations Density 0.011%

    No Known Activations