© 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. 6277
    Prev
    Next
    INDEX
    Explanations

    used for

    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
     grav
    -0.09
    TM
    -0.08
     det
    -0.08
     Commercial
    -0.08
    acre
    -0.08
     prec
    -0.08
     noteworthy
    -0.08
    ney
    -0.08
    anter
    -0.07
     commercial
    -0.07
    POSITIVE LOGITS
     nowadays
    0.14
     traditionally
    0.12
    öh
    0.12
     addictive
    0.12
    ilo
    0.11
     increasingly
    0.11
     notoriously
    0.11
     addict
    0.11
     normally
    0.11
     lifestyle
    0.11
    Activations Density 0.666%

    No Known Activations