© 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. 30376
    Prev
    Next
    INDEX
    Explanations

    said to someone

    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
     posit
    -0.08
     Weinstein
    -0.07
    omen
    -0.07
     Greens
    -0.07
    item
    -0.07
     Russ
    -0.07
    513
    -0.07
    weg
    -0.07
     Andy
    -0.07
    Fine
    -0.07
    POSITIVE LOGITS
     sez
    0.13
     romant
    0.12
     tome
    0.11
     Hin
    0.11
     Hitch
    0.11
     compliment
    0.11
     alas
    0.11
     complained
    0.11
     nostalg
    0.11
     moto
    0.10
    Activations Density 0.015%

    No Known Activations