© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113953
    Prev
    Next
    INDEX
    Explanations

    partner in

    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
    yen
    -0.10
    ness
    -0.10
    erman
    -0.10
    porter
    -0.09
    yard
    -0.09
     mong
    -0.09
     feas
    -0.09
    rd
    -0.09
    /problems
    -0.09
    vel
    -0.09
    POSITIVE LOGITS
    uche
    0.19
    hips
    0.15
    (s
    0.13
    chaft
    0.13
    ials
    0.12
    ization
    0.11
    ially
    0.11
    uml
    0.10
    azzi
    0.10
    ial
    0.10
    Activations Density 0.043%

    No Known Activations