© 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. 17203
    Prev
    Next
    INDEX
    Explanations

    case, anyway, least, license

    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
     perhaps
    -0.14
     possibly
    -0.13
     ideally
    -0.12
    ä½ķ
    -0.12
     Perhaps
    -0.12
     Possibly
    -0.11
    perhaps
    -0.11
    odka
    -0.11
    possibly
    -0.11
     alas
    -0.11
    POSITIVE LOGITS
    bac
    0.10
     concluding
    0.09
     Hind
    0.09
    awe
    0.08
    ened
    0.08
    ario
    0.08
    otto
    0.08
     Directions
    0.07
     Punch
    0.07
     Beta
    0.07
    Activations Density 0.002%

    No Known Activations