© 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. 90916
    Prev
    Next
    INDEX
    Explanations

    review and related contexts

    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
     Calder
    -0.12
    anel
    -0.10
    igit
    -0.09
    ways
    -0.09
    ément
    -0.09
     invaders
    -0.09
    gay
    -0.08
     Cot
    -0.08
    iss
    -0.08
    inning
    -0.08
    POSITIVE LOGITS
    ers
    0.15
    ees
    0.14
    able
    0.13
    er
    0.13
    imonial
    0.11
    /Test
    0.11
    /comment
    0.11
    /test
    0.11
    uated
    0.11
    imony
    0.10
    Activations Density 0.236%

    No Known Activations