© 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. 4530
    Prev
    Next
    INDEX
    Explanations

    principles of

    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
    ness
    -0.09
    abee
    -0.08
     Ramp
    -0.08
     impulse
    -0.07
    ifice
    -0.07
    ev
    -0.07
    thest
    -0.07
    oron
    -0.07
    een
    -0.07
    lick
    -0.07
    POSITIVE LOGITS
     governing
    0.14
     principles
    0.12
    /details
    0.12
     guiding
    0.11
    /components
    0.11
    inz
    0.11
    ually
    0.10
     Principles
    0.10
    Instances
    0.10
    ual
    0.10
    Activations Density 0.022%

    No Known Activations