© 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. 28629
    Prev
    Next
    INDEX
    Explanations

    quotation and attribution

    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
     Bers
    -0.11
     filled
    -0.11
    ibs
    -0.09
     LY
    -0.09
     upto
    -0.09
     lurking
    -0.09
     approx
    -0.08
     unic
    -0.08
     Cha
    -0.08
     Sung
    -0.08
    POSITIVE LOGITS
     pause
    0.10
    lever
    0.10
     Pause
    0.10
    agues
    0.10
    Pause
    0.09
    aines
    0.09
    932
    0.09
    /helper
    0.09
    ailed
    0.09
    Boy
    0.09
    Activations Density 0.059%

    No Known Activations