© 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. 116160
    Prev
    Next
    INDEX
    Explanations

    more than usual/expected/required

    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
     natuur
    -0.09
    uant
    -0.08
    emon
    -0.08
     Becker
    -0.08
     Speakers
    -0.08
    /ca
    -0.08
    quir
    -0.08
    991
    -0.08
    uent
    -0.08
    ailable
    -0.08
    POSITIVE LOGITS
     planned
    0.33
     usual
    0.28
     Planned
    0.25
     scheduled
    0.21
     intended
    0.20
     originally
    0.19
    usual
    0.19
     promised
    0.19
     plan
    0.17
     customary
    0.17
    Activations Density 0.080%

    No Known Activations