© 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. 4652
    Prev
    Next
    INDEX
    Explanations

    is it

    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
     eater
    -0.09
    cond
    -0.09
     refund
    -0.08
    ners
    -0.08
     Cha
    -0.08
    agar
    -0.08
     Dios
    -0.08
    DF
    -0.07
    aris
    -0.07
    odo
    -0.07
    POSITIVE LOGITS
     me
    0.18
     others
    0.15
     am
    0.14
     coincidence
    0.13
    Others
    0.13
    arme
    0.12
     Anyone
    0.12
    Anyone
    0.12
     Others
    0.12
     anyone
    0.12
    Activations Density 0.131%

    No Known Activations