© 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. 49234
    Prev
    Next
    INDEX
    Explanations

    resolutions passed or approving

    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
    avig
    -0.09
     mẽ
    -0.09
    avit
    -0.09
    akov
    -0.08
    quam
    -0.08
    Ñĥ
    -0.08
    dress
    -0.08
    obb
    -0.08
     sore
    -0.08
    odes
    -0.08
    POSITIVE LOGITS
    aries
    0.12
    rgan
    0.11
    æѤåĪ»
    0.10
    ary
    0.10
    encies
    0.10
    itary
    0.10
    дол
    0.10
    otron
    0.10
    æ¡£
    0.10
    ä¹ĭéģĵ
    0.10
    Activations Density 0.024%

    No Known Activations