© 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. 49207
    Prev
    Next
    INDEX
    Explanations

    don't ask / expect / forget

    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
     shouldn
    -0.12
    IOR
    -0.12
    ÑĪе
    -0.11
     parl
    -0.11
    XHR
    -0.11
    (Un
    -0.11
     Hogan
    -0.10
    Bear
    -0.10
    fec
    -0.10
     democrat
    -0.10
    POSITIVE LOGITS
     ask
    0.13
     mistaken
    0.12
     expect
    0.11
     miss
    0.11
     mistake
    0.11
    eni
    0.10
     forget
    0.10
     Expect
    0.10
    Resistance
    0.10
     faint
    0.10
    Activations Density 0.017%

    No Known Activations