© 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. 88903
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
     VII
    -0.14
     Seventh
    -0.13
     Seven
    -0.13
    ï¼ĸ
    -0.12
     seven
    -0.12
     July
    -0.12
    ï¼Ĺ
    -0.12
    7
    -0.12
     seventh
    -0.11
    July
    -0.11
    POSITIVE LOGITS
     tenth
    0.21
    10
    0.20
     ninth
    0.19
     eleven
    0.19
    11
    0.18
    12
    0.17
    9
    0.17
     twelve
    0.17
     ten
    0.16
     nine
    0.16
    Activations Density 0.457%

    No Known Activations