© 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. 47105
    Prev
    Next
    INDEX
    Explanations

    does the

    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
    apo
    -0.08
     Worlds
    -0.07
    ardless
    -0.07
    gc
    -0.07
    vy
    -0.07
     IT
    -0.07
    bits
    -0.06
     ï
    -0.06
    arro
    -0.06
     Boh
    -0.06
    POSITIVE LOGITS
     elsewhere
    0.14
     ones
    0.13
    eli
    0.11
    eft
    0.11
    YW
    0.11
     Vul
    0.11
     Haram
    0.10
    ouri
    0.10
    nya
    0.10
     Micha
    0.10
    Activations Density 0.557%

    No Known Activations