© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 46731
    Prev
    Next
    INDEX
    Explanations

    states or locations

    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
     repos
    -0.11
    /Library
    -0.10
    anel
    -0.10
     pause
    -0.10
     suddenly
    -0.09
     sudden
    -0.09
     hern
    -0.09
    /exp
    -0.09
    lique
    -0.09
    /repos
    -0.09
    POSITIVE LOGITS
     obedient
    0.10
     dumb
    0.09
     consenting
    0.09
    ben
    0.09
     chair
    0.09
    unu
    0.09
     receiving
    0.09
     fixation
    0.09
     ben
    0.08
    lear
    0.08
    Activations Density 0.004%

    No Known Activations