© 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. 4484
    Prev
    Next
    INDEX
    Explanations

    site followed by specific nouns

    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
    ses
    -0.11
    worth
    -0.11
    eron
    -0.10
    noinspection
    -0.09
    oes
    -0.09
    di
    -0.09
    à¹Į
    -0.09
    esse
    -0.09
    /she
    -0.09
    istan
    -0.09
    POSITIVE LOGITS
    -packages
    0.12
    ying
    0.12
    arity
    0.12
    customize
    0.11
    abouts
    0.11
    finity
    0.10
    upon
    0.10
    uality
    0.09
    ç¾Ķ
    0.09
    åŁ
    0.09
    Activations Density 0.058%

    No Known Activations