© 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. 49256
    Prev
    Next
    INDEX
    Explanations

    Ramey, Jamestown, Kamehameha, Tameka

    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
    wall
    -0.08
    /name
    -0.07
    athy
    -0.07
    acker
    -0.07
    name
    -0.07
    words
    -0.06
    names
    -0.06
    wp
    -0.06
     adultes
    -0.06
    teenth
    -0.06
    POSITIVE LOGITS
    cheap
    0.13
     ç±
    0.13
    izin
    0.12
    phis
    0.12
    ISTER
    0.12
    ãĤ«
    0.12
    edly
    0.11
     culpa
    0.11
    adow
    0.11
    stery
    0.11
    Activations Density 0.005%

    No Known Activations