© 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. 25536
    Prev
    Next
    INDEX
    Explanations

    higher comparative

    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
    uso
    -0.12
    ixa
    -0.11
    unning
    -0.11
    ABI
    -0.11
    asz
    -0.11
    alach
    -0.10
    anna
    -0.10
     sympt
    -0.10
     :";↵
    -0.10
     predominantly
    -0.10
    POSITIVE LOGITS
     better
    0.16
     mer
    0.16
     sooner
    0.15
    Better
    0.13
     Better
    0.12
     safer
    0.12
    better
    0.12
     happier
    0.11
    rier
    0.11
     preferably
    0.11
    Activations Density 0.049%

    No Known Activations