© 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. 6641
    Prev
    Next
    INDEX
    Explanations

    clinical data, error data

    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
     mock
    -0.11
     veto
    -0.10
     teasing
    -0.10
     kissed
    -0.09
     tease
    -0.09
     merciless
    -0.09
     shock
    -0.09
     contrary
    -0.09
     orders
    -0.09
     affection
    -0.09
    POSITIVE LOGITS
     nerv
    0.33
     nervous
    0.27
     timid
    0.25
     desperately
    0.22
     desperation
    0.21
     awkward
    0.21
     desperate
    0.20
     anx
    0.20
     cautiously
    0.19
     nerves
    0.19
    Activations Density 0.014%

    No Known Activations