© 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. 17671
    Prev
    Next
    INDEX
    Explanations

    get it

    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
     got
    -0.14
     getting
    -0.13
    got
    -0.12
     Getting
    -0.12
     GET
    -0.12
     Get
    -0.12
     gets
    -0.11
     Got
    -0.11
    _get
    -0.11
     get
    -0.11
    POSITIVE LOGITS
     rid
    0.27
    tin
    0.20
    tings
    0.18
    cha
    0.17
    ters
    0.17
     acquainted
    0.16
     caught
    0.15
    aways
    0.15
     hold
    0.15
     involved
    0.15
    Activations Density 0.144%

    No Known Activations