© 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. 89514
    Prev
    Next
    INDEX
    Explanations

    I can

    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
     stu
    -0.12
     benef
    -0.11
    lete
    -0.10
     Marino
    -0.10
     exiting
    -0.10
    embro
    -0.10
     suce
    -0.10
    /gen
    -0.10
     Arn
    -0.10
     benefiting
    -0.10
    POSITIVE LOGITS
     assure
    0.19
     attest
    0.15
     honestly
    0.14
    't
    0.14
     say
    0.14
     promise
    0.13
     imagine
    0.12
     guarantee
    0.12
     tell
    0.12
    �t
    0.12
    Activations Density 0.055%

    No Known Activations