© 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. 113104
    Prev
    Next
    INDEX
    Explanations

    from [location/source]

    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
    ooks
    -0.11
     Ink
    -0.10
    oret
    -0.10
    avel
    -0.10
    OO
    -0.10
    /catalog
    -0.10
    lsa
    -0.10
    uesday
    -0.10
    rich
    -0.10
    _bd
    -0.10
    POSITIVE LOGITS
     under
    0.10
     where
    0.10
     whence
    0.09
     reflex
    0.08
     waiting
    0.08
     par
    0.08
     sitting
    0.08
     somehow
    0.07
     nurs
    0.07
     strictly
    0.07
    Activations Density 0.065%

    No Known Activations