© 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. 14866
    Prev
    Next
    INDEX
    Explanations

    gently back and forth

    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
     aggressively
    -0.15
     aggressive
    -0.11
     reckless
    -0.11
     frantic
    -0.11
     vigorously
    -0.11
    loud
    -0.10
     boldly
    -0.10
     loud
    -0.10
     loudly
    -0.10
     unab
    -0.10
    POSITIVE LOGITS
     gently
    0.31
     gentle
    0.26
     delic
    0.25
     softly
    0.24
     delicate
    0.23
     slowly
    0.21
     lightly
    0.20
     quietly
    0.19
     Gentle
    0.19
     gent
    0.18
    Activations Density 0.014%

    No Known Activations