© 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. 26041
    Prev
    Next
    INDEX
    Explanations

    code construction and programming

    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
    ULE
    -0.07
    arios
    -0.07
     infr
    -0.07
     Cle
    -0.07
    ittle
    -0.07
     vast
    -0.07
     unearth
    -0.07
    ipo
    -0.07
     heating
    -0.07
    âĻª
    -0.06
    POSITIVE LOGITS
    etc
    0.22
    And
    0.20
    These
    0.19
    and
    0.19
     And
    0.19
    â̦and
    0.18
    AND
    0.17
     These
    0.17
     etc
    0.17
    Additionally
    0.16
    Activations Density 0.961%

    No Known Activations