© 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. 113205
    Prev
    Next
    INDEX
    Explanations

    list 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
     styl
    -0.09
     turquoise
    -0.09
    styl
    -0.08
    obe
    -0.08
     manic
    -0.08
    ista
    -0.08
     propelled
    -0.08
     %#
    -0.07
    xcf
    -0.07
     Tub
    -0.07
    POSITIVE LOGITS
     Pike
    0.12
     freely
    0.11
     Marino
    0.11
     DT
    0.10
    -ST
    0.10
     Slip
    0.10
    ë²Ī
    0.09
    heim
    0.09
     association
    0.09
    ITT
    0.09
    Activations Density 0.036%

    No Known Activations