© 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. 4320
    Prev
    Next
    INDEX
    Explanations

    appearance of

    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
    eros
    -0.10
    inium
    -0.09
    utes
    -0.09
    gles
    -0.09
    unes
    -0.08
    svc
    -0.08
    spot
    -0.08
    åĮIJ
    -0.08
    ä½ĵæ£Ģ
    -0.08
    为广大
    -0.08
    POSITIVE LOGITS
     Borough
    0.09
    lying
    0.09
    æī«ä¸Ģæī«
    0.09
    lick
    0.09
    ment
    0.09
    venir
    0.09
    ettings
    0.08
    æĪijæīį
    0.08
    LIK
    0.08
    ibold
    0.08
    Activations Density 0.024%

    No Known Activations