© 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. 30007
    Prev
    Next
    INDEX
    Explanations

    absent or missing items

    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
    /static
    -0.10
    916
    -0.09
     forgiving
    -0.09
     Impl
    -0.09
    )[-
    -0.08
    ulin
    -0.08
     Chance
    -0.08
     nons
    -0.08
     readdir
    -0.08
     unint
    -0.08
    POSITIVE LOGITS
     absent
    0.65
     absence
    0.54
     missing
    0.50
     disappeared
    0.44
    Absent
    0.44
     disappearance
    0.40
     Missing
    0.39
    missing
    0.38
    ä¸įåŃĺåľ¨
    0.38
    Missing
    0.38
    Activations Density 0.364%

    No Known Activations