© 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. 47831
    Prev
    Next
    INDEX
    Explanations

    certain events would happen

    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
     obviously
    -0.13
     unfortunately
    -0.10
     quite
    -0.10
     оÑĩ
    -0.09
    resh
    -0.09
    lap
    -0.09
     Bits
    -0.09
     much
    -0.09
     understandably
    -0.09
    897
    -0.09
    POSITIVE LOGITS
     "...
    0.12
     “âĢ¦
    0.12
     "..
    0.11
     blah
    0.11
    jec
    0.10
     Pry
    0.10
    ...',
    0.10
     Zu
    0.10
     unspecified
    0.10
     "[
    0.10
    Activations Density 0.184%

    No Known Activations