© 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. 47757
    Prev
    Next
    INDEX
    Explanations

    protein inhibitors and factors

    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
    tent
    -0.09
    yor
    -0.09
    ص
    -0.08
    é
    -0.08
     tent
    -0.08
    mental
    -0.08
    peria
    -0.08
     Mentor
    -0.08
     anyhow
    -0.08
    faculty
    -0.08
    POSITIVE LOGITS
     Le
    0.16
    Le
    0.14
    .Le
    0.14
     le
    0.12
    (le
    0.12
    -Le
    0.11
    -le
    0.11
    _le
    0.09
    _WM
    0.09
    .le
    0.09
    Activations Density 0.344%

    No Known Activations