© 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. 114830
    Prev
    Next
    INDEX
    Explanations

    Carmine, Carmen, Carmel, Carmelo

    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
    orage
    -0.11
    upe
    -0.10
    linger
    -0.10
    hum
    -0.10
     frontier
    -0.09
    uet
    -0.09
    _fre
    -0.09
     prefect
    -0.09
     franch
    -0.09
    imuth
    -0.08
    POSITIVE LOGITS
    hape
    0.10
    itas
    0.10
    asca
    0.09
    igm
    0.09
     rec
    0.09
    rick
    0.09
    /of
    0.09
    cae
    0.09
    etable
    0.09
     Everyday
    0.09
    Activations Density 0.012%

    No Known Activations