© 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. 116398
    Prev
    Next
    INDEX
    Explanations

    thereto or therewith

    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
    ing
    -0.12
    ARAM
    -0.11
    edException
    -0.11
    OrUpdate
    -0.11
    adem
    -0.11
    nowled
    -0.10
    crete
    -0.10
    ServletRequest
    -0.10
    ved
    -0.10
    ingt
    -0.10
    POSITIVE LOGITS
    abouts
    0.12
    fore
    0.11
    upon
    0.11
    oretical
    0.10
     entire
    0.09
     Moff
    0.09
    emer
    0.08
    emin
    0.08
    iegel
    0.08
     Pom
    0.08
    Activations Density 0.002%

    No Known Activations