© 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. 6630
    Prev
    Next
    INDEX
    Explanations

    -burg, -oke, -oc words

    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
    éĢīæĭ
    -0.09
    asco
    -0.09
    èµĬ
    -0.09
    建ç«ĭèµ·
    -0.09
    éªĦ
    -0.09
    å¼ĢçĿĢ
    -0.09
    è·
    -0.09
    æ¿ĢçĥĪçļĦ
    -0.08
    ghan
    -0.08
    Storm
    -0.08
    POSITIVE LOGITS
    ;amp
    0.10
    éĿ¢çĽ®
    0.09
    forc
    0.09
    åIJģ
    0.08
    iveness
    0.08
    IKE
    0.08
    uristic
    0.08
    rolls
    0.08
    chest
    0.08
    à¹Ħ
    0.08
    Activations Density 0.001%

    No Known Activations