© 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. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 47738
    Prev
    Next
    INDEX
    Explanations

    starts with "what"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_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
     appalling
    -0.09
     iff
    -0.08
     Undefined
    -0.08
    .before
    -0.07
    LOC
    -0.07
    vl
    -0.07
     VERY
    -0.07
     disgusting
    -0.07
     unfamiliar
    -0.07
    /bind
    -0.07
    POSITIVE LOGITS
     what
    0.31
    what
    0.27
     What
    0.26
    What
    0.24
    ä½ķ
    0.22
     WHAT
    0.21
    .what
    0.21
     whats
    0.19
    WHAT
    0.18
    .What
    0.18
    Activations Density 0.107%

    No Known Activations