© 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. 28809
    Prev
    Next
    INDEX
    Explanations

    strength and power

    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
    ting
    -0.09
     richt
    -0.09
    ICC
    -0.09
    chied
    -0.09
    TING
    -0.09
    odo
    -0.09
    Sab
    -0.09
    unga
    -0.09
    cing
    -0.08
     Sab
    -0.08
    POSITIVE LOGITS
    holds
    0.27
    (er
    0.19
    hold
    0.16
    lings
    0.14
    /fast
    0.12
    /power
    0.12
    /we
    0.11
    -hearted
    0.11
    esti
    0.11
    heart
    0.11
    Activations Density 0.072%

    No Known Activations