© 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. 25938
    Prev
    Next
    INDEX
    Explanations

    alone, plus, excluding, each, depending

    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
    ubi
    -0.10
     extensively
    -0.09
     thrust
    -0.09
     pragmatic
    -0.09
    DMI
    -0.09
     especially
    -0.08
     fab
    -0.08
    olini
    -0.08
     Adapt
    -0.08
     inline
    -0.08
    POSITIVE LOGITS
     alone
    0.19
    alone
    0.17
     plus
    0.15
     PLUS
    0.15
    excluding
    0.14
     excluding
    0.14
     EACH
    0.14
    depending
    0.13
     Alone
    0.13
    plus
    0.12
    Activations Density 0.903%

    No Known Activations