© 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. 29781
    Prev
    Next
    INDEX
    Explanations

    will/can/am/want + verb

    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
    arez
    -0.11
    chn
    -0.10
     yourselves
    -0.10
    /close
    -0.10
    _tests
    -0.10
    coc
    -0.10
    ivi
    -0.10
     nou
    -0.09
     Dove
    -0.09
     perhaps
    -0.09
    POSITIVE LOGITS
     accompanying
    0.09
     Worst
    0.09
     bis
    0.09
    abin
    0.08
     Bul
    0.08
     accompanies
    0.08
    owie
    0.08
     worst
    0.08
    wor
    0.08
    Auth
    0.08
    Activations Density 0.055%

    No Known Activations