© 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. 49549
    Prev
    Next
    INDEX
    Explanations

    questions about what is

    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
     somehow
    -0.13
     Somehow
    -0.10
     strangely
    -0.10
     too
    -0.09
     despite
    -0.09
     fortunately
    -0.08
     unfortunately
    -0.08
     surprisingly
    -0.08
     TOO
    -0.08
     LOT
    -0.08
    POSITIVE LOGITS
     constantly
    0.15
     potentially
    0.14
     clearly
    0.12
     essentially
    0.12
     demonstr
    0.12
     fundamentally
    0.11
     literally
    0.11
     Kal
    0.11
     continually
    0.11
    abis
    0.11
    Activations Density 0.090%

    No Known Activations