© 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. 29278
    Prev
    Next
    INDEX
    Explanations

    telling someone something

    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
     EITHER
    -0.09
    ilig
    -0.09
    (cos
    -0.09
    .mid
    -0.08
    adiens
    -0.08
     diameter
    -0.08
    /use
    -0.08
     considerably
    -0.08
     hanging
    -0.08
     diam
    -0.08
    POSITIVE LOGITS
    åijĬ
    0.14
     told
    0.14
     telling
    0.14
     tell
    0.13
     tells
    0.13
     reporters
    0.12
     instruct
    0.11
    tell
    0.11
     everybody
    0.11
     them
    0.11
    Activations Density 0.007%

    No Known Activations