© 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. 88440
    Prev
    Next
    INDEX
    Explanations

    usage examples and definitions

    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
     Suff
    -0.10
     Vibr
    -0.10
    elif
    -0.09
     Hairst
    -0.09
     reader
    -0.09
     Verm
    -0.09
    umbs
    -0.09
     vibr
    -0.08
    hana
    -0.08
    abis
    -0.08
    POSITIVE LOGITS
     synonym
    0.16
     synonyms
    0.13
     Usage
    0.13
     USAGE
    0.13
     Examples
    0.12
    "She
    0.12
    "He
    0.12
     Example
    0.12
    ä¾ĭ
    0.11
    Examples
    0.11
    Activations Density 0.071%

    No Known Activations