© 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. 50437
    Prev
    Next
    INDEX
    Explanations

    task completion

    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
     Ful
    -0.09
     hardest
    -0.09
     dominant
    -0.09
    ano
    -0.08
    acho
    -0.08
    onas
    -0.08
     grp
    -0.08
     fulfil
    -0.08
     expend
    -0.08
    /ac
    -0.08
    POSITIVE LOGITS
     menstr
    0.11
     marvel
    0.10
    ked
    0.10
     Dish
    0.10
    506
    0.09
    433
    0.09
     instruct
    0.09
    ibs
    0.09
    539
    0.09
     reminis
    0.09
    Activations Density 0.016%

    No Known Activations