© 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. 53008
    Prev
    Next
    INDEX
    Explanations

    plaque development or burden

    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
    esto
    -0.11
    PerPixel
    -0.09
    eties
    -0.09
    thon
    -0.09
    liner
    -0.09
    thic
    -0.09
    girl
    -0.09
    ients
    -0.09
    lyph
    -0.09
    æ²¹
    -0.08
    POSITIVE LOGITS
    holder
    0.10
    ../../../
    0.10
    amel
    0.10
    mates
    0.09
    累累
    0.09
    aber
    0.09
    holders
    0.09
    mate
    0.09
    HOLDER
    0.09
    åĥµ
    0.09
    Activations Density 0.020%

    No Known Activations