© 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. 3665
    Prev
    Next
    INDEX
    Explanations

    recreation services and activities

    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
    à¸Ĭะ
    -0.11
    GED
    -0.10
    pering
    -0.09
    åŃIJéĩĮ
    -0.09
    atis
    -0.09
    ness
    -0.09
    odia
    -0.09
    æįĤ
    -0.09
    rox
    -0.09
    å¤ĸåįĸ
    -0.09
    POSITIVE LOGITS
    ally
    0.15
    ../../../
    0.11
    lei
    0.10
    .gov
    0.09
    ively
    0.09
    naissance
    0.09
    /social
    0.08
     havoc
    0.08
    ãģĦãģĨ
    0.08
     Emin
    0.08
    Activations Density 0.005%

    No Known Activations