© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90049
    Prev
    Next
    INDEX
    Explanations

    combat

    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
    holding
    -0.12
    icot
    -0.10
    ISCO
    -0.10
    holds
    -0.10
    poke
    -0.09
    chaft
    -0.09
    emand
    -0.09
     guts
    -0.09
    hd
    -0.09
     keeper
    -0.09
    POSITIVE LOGITS
    ting
    0.23
    ants
    0.23
    ant
    0.17
    iveness
    0.16
    erea
    0.14
    -ready
    0.13
    ible
    0.13
    ibility
    0.13
     effectiveness
    0.13
     readiness
    0.12
    Activations Density 0.044%

    No Known Activations