© 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. 30201
    Prev
    Next
    INDEX
    Explanations

    continuous effort and progress

    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
    /OR
    -0.12
     unfolding
    -0.11
    umpt
    -0.11
    eko
    -0.11
     bump
    -0.10
     rematch
    -0.10
     nostalg
    -0.10
    âĢİ
    -0.10
     freely
    -0.10
    memo
    -0.10
    POSITIVE LOGITS
     relentless
    0.16
     steady
    0.14
     constant
    0.14
     pace
    0.14
     pressure
    0.13
     effort
    0.12
     continuous
    0.12
     assaults
    0.12
     tempo
    0.12
     onslaught
    0.12
    Activations Density 0.023%

    No Known Activations