© 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. 18825
    Prev
    Next
    INDEX
    Explanations

    front page article

    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
    é¢ijéģĵ
    -0.12
    鸨
    -0.10
    .Skin
    -0.10
     CHANNEL
    -0.10
     ÙĤÙĨاة
    -0.10
    åĪ»èĭ¦
    -0.10
    éĵ¶è¡Įä¸ļ
    -0.10
    éªĸ
    -0.09
    çŀİ
    -0.09
    使èĢħ
    -0.09
    POSITIVE LOGITS
    åłĤ
    0.09
    Min
    0.09
     Homepage
    0.08
     sco
    0.08
    æݥ管
    0.08
    åĪ®
    0.08
    亲身
    0.08
    engo
    0.08
    æijĬ
    0.08
    åĬłå¼º
    0.08
    Activations Density 0.029%

    No Known Activations