© 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. 92035
    Prev
    Next
    INDEX
    Explanations

    complex followed by 's', 'ed', 'ation', 'type'

    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
    bled
    -0.10
    bling
    -0.10
    ning
    -0.10
    NING
    -0.09
    nik
    -0.09
    VENT
    -0.09
    pla
    -0.09
    rog
    -0.09
    fulness
    -0.09
    asel
    -0.09
    POSITIVE LOGITS
    ed
    0.18
    es
    0.17
    (es
    0.17
    ioned
    0.16
    ation
    0.15
    ions
    0.15
    tures
    0.13
    ing
    0.12
    ified
    0.11
    ification
    0.11
    Activations Density 0.039%

    No Known Activations