© 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. 62082
    Prev
    Next
    INDEX
    Explanations

    pt or PT

    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
    å¥ī
    -0.10
    strate
    -0.10
    éħ¿
    -0.10
    erate
    -0.09
     Crunch
    -0.09
    bia
    -0.09
     Cowboys
    -0.09
    éĻ¢å£«
    -0.09
    _AMD
    -0.09
    tron
    -0.08
    POSITIVE LOGITS
    pto
    0.10
    tern
    0.10
    annie
    0.10
    amina
    0.10
     PT
    0.09
    icular
    0.09
    ioned
    0.09
    (pts
    0.09
    èĥĦ
    0.09
    ake
    0.09
    Activations Density 0.033%

    No Known Activations