© 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. 28782
    Prev
    Next
    INDEX
    Explanations

    doesn't need fixing

    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
    rst
    -0.10
     Florence
    -0.09
     reg
    -0.08
    neider
    -0.08
     hardened
    -0.08
     scorn
    -0.08
     desp
    -0.08
    wald
    -0.08
    087
    -0.08
     omitted
    -0.08
    POSITIVE LOGITS
     unchanged
    0.17
     stable
    0.16
     perfection
    0.16
     inertia
    0.16
     satisfactory
    0.16
     perfectly
    0.15
     satisfied
    0.15
     comfortable
    0.14
     satisf
    0.13
     successful
    0.13
    Activations Density 0.309%

    No Known Activations