© 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. 5116
    Prev
    Next
    INDEX
    Explanations

    auction

    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
    hood
    -0.10
    lessness
    -0.10
    lessly
    -0.09
    ament
    -0.09
    è²Į
    -0.08
    ult
    -0.08
    fait
    -0.08
    heit
    -0.08
    ities
    -0.08
    gence
    -0.08
    POSITIVE LOGITS
    eer
    0.19
    ën
    0.11
    ees
    0.11
    رة
    0.10
    äºĨå¤ļå°ij
    0.10
    strar
    0.10
    naire
    0.10
    tá
    0.10
    FileVersion
    0.09
    æĺİçĻ½äºĨ
    0.09
    Activations Density 0.005%

    No Known Activations