© 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. 116484
    Prev
    Next
    INDEX
    Explanations

    places where conflicts or significant events occur

    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
     Nearly
    -0.07
    ffb
    -0.07
     nearly
    -0.07
    anni
    -0.07
    HS
    -0.07
     McCorm
    -0.07
     additionally
    -0.07
     Barth
    -0.07
     continually
    -0.07
     purchasers
    -0.07
    POSITIVE LOGITS
     folks
    0.14
     learnt
    0.14
     duly
    0.14
     dude
    0.13
     Lagos
    0.13
     stuff
    0.13
     goodies
    0.13
     erst
    0.13
     unto
    0.12
     ain
    0.12
    Activations Density 0.001%

    No Known Activations