© 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. 5365
    Prev
    Next
    INDEX
    Explanations

    compressing or compressed files

    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
    rimon
    -0.10
    itch
    -0.09
    abouts
    -0.09
    fulness
    -0.09
    .uk
    -0.08
    ivers
    -0.08
    YTE
    -0.08
    aju
    -0.08
    vertis
    -0.08
    wer
    -0.08
    POSITIVE LOGITS
    ible
    0.12
    縮
    0.11
    عÙĦ
    0.10
    ingly
    0.10
    ibility
    0.10
    dw
    0.10
    æŁł
    0.10
    /stretch
    0.09
    ensible
    0.09
    åľ°å¸¦
    0.08
    Activations Density 0.029%

    No Known Activations