© 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. 89773
    Prev
    Next
    INDEX
    Explanations

    poster / posters

    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
    ichten
    -0.10
    umped
    -0.09
     comm
    -0.09
    ments
    -0.09
     refr
    -0.09
    licht
    -0.08
     discharged
    -0.08
     Via
    -0.08
     reap
    -0.08
     ident
    -0.08
    POSITIVE LOGITS
    edm
    0.11
     Arnold
    0.10
    lew
    0.09
     Edwin
    0.09
    imir
    0.09
     xPos
    0.09
     Shay
    0.09
    -Ass
    0.09
     stringValue
    0.09
     Xml
    0.09
    Activations Density 0.002%

    No Known Activations