© 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. 29968
    Prev
    Next
    INDEX
    Explanations

    initially from scratch

    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
     decrement
    -0.12
     Decay
    -0.11
    ldb
    -0.11
     Autonomous
    -0.11
     Jeg
    -0.11
     Haut
    -0.11
     farewell
    -0.11
     Tried
    -0.11
     fading
    -0.11
    KM
    -0.11
    POSITIVE LOGITS
     empty
    0.24
     dormant
    0.21
     nonexistent
    0.20
     barren
    0.20
     initially
    0.19
     inactive
    0.19
    empty
    0.19
     blank
    0.18
     negligible
    0.17
     Empty
    0.17
    Activations Density 1.088%

    No Known Activations