© 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. 88449
    Prev
    Next
    INDEX
    Explanations

    credit or origin

    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
    893
    -0.09
     monopoly
    -0.09
     Keywords
    -0.09
     monopol
    -0.09
     specially
    -0.09
     smuggling
    -0.08
    agh
    -0.08
     Mann
    -0.08
     Sass
    -0.08
    929
    -0.08
    POSITIVE LOGITS
     credit
    0.31
     credited
    0.30
     credits
    0.29
     Credit
    0.25
     attribution
    0.25
    credited
    0.24
    credit
    0.23
    Credit
    0.23
     Credits
    0.23
    _credit
    0.22
    Activations Density 0.296%

    No Known Activations