© 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. 46656
    Prev
    Next
    INDEX
    Explanations

    shapes and paths

    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
    IFT
    -0.09
     locale
    -0.09
     lately
    -0.09
    oter
    -0.09
     flock
    -0.09
     prow
    -0.09
     locally
    -0.09
     Chronicles
    -0.08
    lete
    -0.08
    uten
    -0.08
    POSITIVE LOGITS
     patterns
    0.14
     circles
    0.14
     across
    0.13
     rhythm
    0.12
     havoc
    0.12
     holes
    0.12
    ean
    0.12
     onto
    0.11
     marks
    0.11
     path
    0.11
    Activations Density 0.002%

    No Known Activations