© 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. 17388
    Prev
    Next
    INDEX
    Explanations

    the objective of

    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
     reveal
    -0.12
     illust
    -0.11
    tram
    -0.11
     occup
    -0.10
     temperament
    -0.10
     Paras
    -0.10
     Salvation
    -0.10
     prophecy
    -0.10
     Straw
    -0.10
     breed
    -0.09
    POSITIVE LOGITS
    oretical
    0.15
     role
    0.15
     Role
    0.14
     centr
    0.14
    role
    0.13
    oria
    0.12
    ories
    0.12
    or
    0.12
     Machinery
    0.11
     quest
    0.11
    Activations Density 2.405%

    No Known Activations