© 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. 91702
    Prev
    Next
    INDEX
    Explanations

    off-

    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
     off
    -0.17
    offs
    -0.14
     Off
    -0.13
    off
    -0.13
    -offs
    -0.13
     offshore
    -0.12
     OFF
    -0.12
    iform
    -0.12
    OFF
    -0.12
    rowse
    -0.11
    POSITIVE LOGITS
    ensively
    0.23
    shoot
    0.19
    site
    0.17
    /on
    0.16
    icer
    0.16
    beat
    0.14
    spring
    0.14
    ensive
    0.14
    -road
    0.14
    screen
    0.13
    Activations Density 0.105%

    No Known Activations