© 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. 117184
    Prev
    Next
    INDEX
    Explanations

    on an "AS IS" BASIS

    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
    bum
    -0.10
     Viewing
    -0.10
     redistribute
    -0.09
     Specs
    -0.09
     comfy
    -0.09
    827
    -0.09
     Filed
    -0.09
     restrain
    -0.09
    usk
    -0.08
     freeze
    -0.08
    POSITIVE LOGITS
     simultaneously
    0.16
     causing
    0.14
     coupled
    0.14
     combined
    0.14
     elic
    0.13
     resulted
    0.13
    elic
    0.13
     combination
    0.13
     causes
    0.13
     result
    0.12
    Activations Density 0.020%

    No Known Activations