© 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. 30901
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by verb or adjective

    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
    okie
    -0.07
    aise
    -0.07
    iac
    -0.07
     plurality
    -0.07
     glitch
    -0.06
     Hawkins
    -0.06
     Aust
    -0.06
     intimacy
    -0.06
     congress
    -0.06
     inters
    -0.06
    POSITIVE LOGITS
    maj
    0.13
    Called
    0.13
     Called
    0.12
     maj
    0.12
     Maj
    0.12
    /man
    0.12
     Came
    0.12
     remembered
    0.11
    .bp
    0.11
     thirst
    0.11
    Activations Density 0.033%

    No Known Activations