© 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. 14968
    Prev
    Next
    INDEX
    Explanations

    case numbers or identifiers

    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
    lav
    -0.09
     Berger
    -0.09
     rent
    -0.09
     purchasing
    -0.08
     Hague
    -0.08
     enumerated
    -0.08
    houses
    -0.08
     leasing
    -0.08
     commissions
    -0.08
    @a
    -0.08
    POSITIVE LOGITS
     dated
    0.12
    RSS
    0.10
    Branch
    0.10
     Bom
    0.10
     tremend
    0.10
    branch
    0.10
     eff
    0.10
     Emin
    0.10
    angep
    0.10
     tween
    0.10
    Activations Density 1.081%

    No Known Activations