© 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. 57896
    Prev
    Next
    INDEX
    Explanations

    foreign entities or policies

    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
    ä¸ĸçķĮä¸Ĭ
    -0.09
    IMUM
    -0.09
    ç¥ĵ
    -0.09
    æĢ»ä½ĵè§ĦåĪĴ
    -0.09
    ail
    -0.09
    ixer
    -0.08
     Skywalker
    -0.08
    uate
    -0.08
    åıªè¦ģä½ł
    -0.08
    åIJij社ä¼ļ
    -0.08
    POSITIVE LOGITS
    ity
    0.12
    ness
    0.11
    à¹ĥà¸Ī
    0.10
    EST
    0.10
    -language
    0.10
    liness
    0.10
    -facing
    0.09
    most
    0.09
    er
    0.09
    rance
    0.09
    Activations Density 0.022%

    No Known Activations