© 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. 17562
    Prev
    Next
    INDEX
    Explanations

    at the level of

    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
    orang
    -0.12
    metro
    -0.11
    aga
    -0.11
     Schul
    -0.11
     setHidden
    -0.11
    enze
    -0.11
    abox
    -0.10
    UpDown
    -0.10
    addy
    -0.10
     Gloss
    -0.10
    POSITIVE LOGITS
     level
    0.40
     levels
    0.30
     Level
    0.29
     LEVEL
    0.27
    level
    0.26
    _level
    0.25
    Level
    0.24
     niveau
    0.24
     Levels
    0.23
    LEVEL
    0.21
    Activations Density 0.163%

    No Known Activations