© 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. 23179
    Prev
    Next
    INDEX
    Explanations

    aimed at / geared toward

    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
    æī®
    -0.09
    cctor
    -0.09
    èĽ°
    -0.08
    转åĬ¨
    -0.08
    ÙĬات
    -0.08
    é¢ĨæĤŁ
    -0.08
    亲çĪ±
    -0.08
    æĺī
    -0.08
    .Configuration
    -0.08
    å±ĢéĿ¢
    -0.08
    POSITIVE LOGITS
    æIJŀ
    0.12
    å®ĮäºĨ
    0.11
    追æ±Ĥ
    0.10
    åĥĸ
    0.10
    æIJŀ好
    0.10
    igned
    0.10
    ä¸įæŃ»
    0.10
    éĩį建
    0.09
    åĿ¡
    0.09
    æŁIJ个
    0.09
    Activations Density 0.041%

    No Known Activations