© 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. 26108
    Prev
    Next
    INDEX
    Explanations

    side of body parts

    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
    alin
    -0.11
    uw
    -0.11
    oled
    -0.10
    IVEN
    -0.10
    atu
    -0.10
    ein
    -0.10
    suite
    -0.10
     Sponsored
    -0.10
    SetActive
    -0.10
    idar
    -0.10
    POSITIVE LOGITS
     else
    0.08
     yielding
    0.07
    ÑĢаÑĤ
    0.07
    hta
    0.07
     otherwise
    0.07
     Lambert
    0.07
    razier
    0.07
     Dt
    0.07
     chem
    0.07
    239
    0.06
    Activations Density 0.006%

    No Known Activations