© 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. 91439
    Prev
    Next
    INDEX
    Explanations

    numbers after dollar signs, or dates, or code comments

    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
    elin
    -0.10
     Hur
    -0.09
     McA
    -0.08
    efs
    -0.08
     Brett
    -0.08
    cka
    -0.08
     conc
    -0.08
    emente
    -0.08
    Gatt
    -0.07
     correl
    -0.07
    POSITIVE LOGITS
    variants
    0.11
    OULD
    0.11
    ás
    0.10
     meny
    0.10
    iesz
    0.10
    Sanders
    0.10
     getRequest
    0.10
    inan
    0.10
    ingt
    0.10
     mint
    0.09
    Activations Density 0.066%

    No Known Activations