© 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. 48654
    Prev
    Next
    INDEX
    Explanations

    chin cord/ups/ensis/chinatown/chinaware

    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
     Binary
    -0.13
    ghi
    -0.12
    er
    -0.11
     pinned
    -0.11
    .cgi
    -0.11
     Frost
    -0.11
     silenced
    -0.11
    erial
    -0.11
     rash
    -0.10
    esch
    -0.10
    POSITIVE LOGITS
    strap
    0.10
     jaws
    0.10
     jaw
    0.08
    bones
    0.08
     cavity
    0.08
    DDS
    0.08
     discre
    0.08
     Boyle
    0.08
    pty
    0.08
     temples
    0.08
    Activations Density 0.002%

    No Known Activations