© 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. 55696
    Prev
    Next
    INDEX
    Explanations

    counts of items

    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
    éĽ¹
    -0.11
    äºĶåįĥ
    -0.09
    人士
    -0.09
    äºĮåįģåĽĽ
    -0.09
    wald
    -0.08
    åĺīå¹´
    -0.08
    Contained
    -0.08
    REET
    -0.08
    åıijå±ķ缮æłĩ
    -0.08
    imedia
    -0.08
    POSITIVE LOGITS
    ä¸ī个
    0.12
    åĽĽä¸ª
    0.11
    åĩłä¸ª
    0.10
    个å°ı
    0.10
    好åĩłä¸ª
    0.10
    两åIJį
    0.10
    ä¸Ģ个å°ı
    0.10
     several
    0.10
    两个
    0.10
    ä¸įæŃ¢
    0.09
    Activations Density 0.355%

    No Known Activations