© 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. 61394
    Prev
    Next
    INDEX
    Explanations

    whiskey and bourbon

    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
    SHIP
    -0.10
    å¾ĹæĦı
    -0.10
    ored
    -0.09
    ofil
    -0.09
    çļĦä½ľåĵģ
    -0.09
    翳
    -0.09
     cứ
    -0.09
    积æŀģéħįåIJĪ
    -0.09
    /up
    -0.09
    lient
    -0.09
    POSITIVE LOGITS
    trs
    0.10
    metro
    0.09
     viet
    0.09
    ftware
    0.09
    berger
    0.09
    ilos
    0.08
    tracts
    0.08
    rai
    0.08
    emu
    0.08
    atten
    0.08
    Activations Density 0.002%

    No Known Activations