© 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. 116113
    Prev
    Next
    INDEX
    Explanations

    unmet expectations

    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
     Jas
    -0.12
     Notices
    -0.10
    esc
    -0.10
    idos
    -0.10
     Tay
    -0.09
     unusual
    -0.09
     increasingly
    -0.09
    Ac
    -0.09
     orphan
    -0.09
     Progress
    -0.09
    POSITIVE LOGITS
     disappoint
    0.37
     disappointing
    0.34
     disappointment
    0.33
     disappointed
    0.28
     expectations
    0.21
     antic
    0.17
     expected
    0.17
     disillusion
    0.17
     fulfilling
    0.17
     hype
    0.16
    Activations Density 0.218%

    No Known Activations