© 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. 18596
    Prev
    Next
    INDEX
    Explanations

    religious buildings, freedom, figure, services, complexes, radio, liberty, text

    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
    ÑĩаÑĤ
    -0.10
    Ñħож
    -0.09
     ÑĢемонÑĤ
    -0.09
    Ñīик
    -0.09
    åĽŀäºĭ
    -0.09
    ä¸Ģ级
    -0.09
    黼
    -0.09
    aceous
    -0.09
    thesis
    -0.09
    åĴ½
    -0.09
    POSITIVE LOGITS
    LY
    0.14
    ly
    0.13
    çĶ¨åĵģ
    0.12
    ness
    0.11
    NESS
    0.10
    fulness
    0.10
    ongyang
    0.09
    ably
    0.09
    earch
    0.09
    zza
    0.09
    Activations Density 0.006%

    No Known Activations