© 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. 32625
    Prev
    Next
    INDEX
    Explanations

    saying something again

    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
     repeatedly
    -0.16
     continuing
    -0.13
     repeat
    -0.13
     repeated
    -0.13
     further
    -0.13
     continued
    -0.12
     continue
    -0.12
    repeat
    -0.12
     continues
    -0.12
     Repeat
    -0.12
    POSITIVE LOGITS
     louder
    0.11
    tz
    0.09
     softer
    0.09
     emphas
    0.09
     slower
    0.09
     omin
    0.08
    esper
    0.08
     emphasizing
    0.08
     eer
    0.08
     emph
    0.08
    Activations Density 0.005%

    No Known Activations