© 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. 39220
    Prev
    Next
    INDEX
    Explanations

    trophies, title, first

    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
     coz
    -0.08
    çģ«å±±
    -0.08
    æīĵå¾Ĺ
    -0.08
    _GF
    -0.08
     deal
    -0.08
    mates
    -0.07
    .getLocal
    -0.07
    æĢ»æĬķèµĦ
    -0.07
    æĪIJçĨŁçļĦ
    -0.07
    mate
    -0.07
    POSITIVE LOGITS
    äºĶéĩij
    0.12
    ä¸ļä½Ļ
    0.11
    éĺĸ
    0.10
    æľįåĬ¡å¹³åı°
    0.10
    å¥ĸ项
    0.10
    çĶµå½±èĬĤ
    0.10
    累累
    0.10
    夺åĨł
    0.10
    é¢Ĩåıĸ
    0.10
    æIJª
    0.09
    Activations Density 0.113%

    No Known Activations