© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37668
    Prev
    Next
    INDEX
    Explanations

    proper names ending in -ard or -er

    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
    è¤IJèī²
    -0.10
    éĢĤå®ľ
    -0.09
    çİĭåºľ
    -0.09
    ä¿Ł
    -0.09
    èĭĭ
    -0.09
    hone
    -0.09
    èĥ§
    -0.09
    igt
    -0.09
    éĩįéĩį
    -0.09
    lore
    -0.08
    POSITIVE LOGITS
     Ñģобой
    0.09
    odiac
    0.09
    ope
    0.08
    _PED
    0.08
    eter
    0.08
     studs
    0.08
    ãģĦãģĨ
    0.08
     Stall
    0.08
    EMU
    0.08
    ../../../
    0.07
    Activations Density 0.004%

    No Known Activations