© 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. 17644
    Prev
    Next
    INDEX
    Explanations

    Laura followed by a name

    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
    enance
    -0.11
    TING
    -0.11
    iator
    -0.10
     Quart
    -0.10
    ertext
    -0.10
    iate
    -0.09
    º
    -0.09
    iated
    -0.09
    oria
    -0.09
    ãĤ¡
    -0.09
    POSITIVE LOGITS
    ivals
    0.10
    .LayoutParams
    0.10
    inal
    0.09
     shutter
    0.09
    unk
    0.09
    ราว
    0.09
    inals
    0.08
    .ide
    0.08
    liest
    0.08
    weise
    0.08
    Activations Density 0.021%

    No Known Activations