© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 4145
    Prev
    Next
    INDEX
    Explanations

    mathematical derivative or number

    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
     Epic
    -0.09
     Bannon
    -0.09
     phot
    -0.09
    /drivers
    -0.09
     Goose
    -0.08
     dial
    -0.08
     tear
    -0.08
    869
    -0.08
    beck
    -0.08
    esco
    -0.08
    POSITIVE LOGITS
     respectful
    0.13
     mutually
    0.11
    ÙĪØ¯
    0.10
    assandra
    0.10
     UserID
    0.10
    _Man
    0.09
     tot
    0.09
     reflex
    0.09
     respectfully
    0.09
     Respect
    0.09
    Activations Density 0.001%

    No Known Activations