© 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. 48744
    Prev
    Next
    INDEX
    Explanations

    word separator hyphen

    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
     Lamb
    -0.09
    &type
    -0.09
     abound
    -0.08
     PLACE
    -0.08
    mour
    -0.08
    ochond
    -0.08
    ktor
    -0.08
     concentrate
    -0.07
     Ort
    -0.07
    etu
    -0.07
    POSITIVE LOGITS
    /OR
    0.15
    /or
    0.11
     Nos
    0.11
    self
    0.10
    --↵
    0.10
    alm
    0.10
    -and
    0.10
     bark
    0.10
    quot
    0.09
    Jos
    0.09
    Activations Density 0.035%

    No Known Activations