© 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. 116260
    Prev
    Next
    INDEX
    Explanations

    does not feel right

    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
     puzz
    -0.13
     curiosity
    -0.12
     perplex
    -0.12
     apparently
    -0.11
     bewild
    -0.11
     Dios
    -0.10
     labyrinth
    -0.10
    endale
    -0.10
    IOS
    -0.10
     confusion
    -0.09
    POSITIVE LOGITS
     appropriately
    0.10
     somehow
    0.10
     Strauss
    0.10
     appropriate
    0.09
     credential
    0.09
    âĢ¦..
    0.09
    appropri
    0.09
     fitting
    0.08
     dep
    0.08
    âĢ¦
    0.08
    Activations Density 0.032%

    No Known Activations