© 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. 36469
    Prev
    Next
    INDEX
    Explanations

    drawings

    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
    astes
    -0.09
     Bund
    -0.09
    åŃļ
    -0.08
    ân
    -0.08
    коло
    -0.08
    åħ±åĴĮåĽ½
    -0.08
    åıĽ
    -0.08
    noop
    -0.08
    :path
    -0.08
    .dup
    -0.08
    POSITIVE LOGITS
    åĽ¾çº¸
    0.19
     drawings
    0.11
    ä¸įæĺİçĻ½
    0.11
    泡
    0.10
    é½IJåħ¨
    0.10
    èįīæ¡Ī
    0.10
    å®Įå¤ĩ
    0.10
    ä¸Ģè¾¹
    0.09
     dra
    0.09
    æķ¢
    0.09
    Activations Density 0.046%

    No Known Activations