© 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. 114072
    Prev
    Next
    INDEX
    Explanations

    programming code and examples

    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
    @update
    -0.12
    @dynamic
    -0.11
    NotFoundError
    -0.10
    /Dk
    -0.10
    -valu
    -0.10
     MethodInvocation
    -0.09
    igli
    -0.09
    _ENSURE
    -0.09
    ñana
    -0.09
     bricks
    -0.09
    POSITIVE LOGITS
     exh
    0.11
     gently
    0.10
     attempted
    0.10
     replied
    0.09
     ar
    0.09
     spraw
    0.09
     stif
    0.09
     motion
    0.08
     said
    0.08
     apologise
    0.08
    Activations Density 0.003%

    No Known Activations