© 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. 112586
    Prev
    Next
    INDEX
    Explanations

    move, put, drag, throw

    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
     Associates
    -0.08
     skies
    -0.08
    lingen
    -0.08
    374
    -0.08
     appl
    -0.08
    grounds
    -0.08
     conco
    -0.08
    ses
    -0.07
     implicated
    -0.07
    FX
    -0.07
    POSITIVE LOGITS
     seated
    0.12
     helicopt
    0.11
     relocated
    0.11
     Ged
    0.11
    移åĪ°
    0.10
     disappearing
    0.10
    amat
    0.10
     Autof
    0.10
     deposited
    0.10
    Scaled
    0.10
    Activations Density 0.016%

    No Known Activations