© 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. 6875
    Prev
    Next
    INDEX
    Explanations

    based statements

    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
     nond
    -0.09
    erable
    -0.09
    aya
    -0.08
    eam
    -0.08
     Holl
    -0.07
     prot
    -0.07
     Brennan
    -0.07
    iek
    -0.07
     actively
    -0.07
    egt
    -0.07
    POSITIVE LOGITS
     based
    0.22
    based
    0.18
     upon
    0.18
     decisions
    0.18
     Based
    0.18
    sole
    0.16
     Sole
    0.16
    Based
    0.16
     solely
    0.15
     hinge
    0.15
    Activations Density 0.227%

    No Known Activations