© 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. 6846
    Prev
    Next
    INDEX
    Explanations

    file prefixes or code structures

    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
    ease
    -0.10
    åħ³å¿ĥ
    -0.09
    çijķ
    -0.08
    åijĬ
    -0.08
     ANSI
    -0.08
     Deutsch
    -0.08
    çĶļ
    -0.08
    åĴ¤
    -0.08
    atz
    -0.08
    èĻ»
    -0.07
    POSITIVE LOGITS
    æīĢåľ¨åľ°
    0.10
    strup
    0.10
    è¿ĩåī©
    0.09
    comm
    0.09
    æ¯į亲
    0.09
    解æĶ¾æĢĿæĥ³
    0.09
    ç¼°
    0.09
    æĮģç»Ńæİ¨è¿Ľ
    0.09
    è¦ģä¹Ī
    0.09
    PathComponent
    0.09
    Activations Density 0.261%

    No Known Activations