© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31401
    Prev
    Next
    INDEX
    Explanations

    ep endings

    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
     Killer
    -0.11
    ewise
    -0.10
     voc
    -0.09
     killer
    -0.09
    iram
    -0.09
    uten
    -0.08
    epad
    -0.08
     arm
    -0.08
     Darwin
    -0.08
    sett
    -0.08
    POSITIVE LOGITS
    hist
    0.12
    hr
    0.12
    isodes
    0.11
    itel
    0.10
    ublic
    0.10
     Gott
    0.10
    si
    0.10
    ISODE
    0.10
    ers
    0.09
    ember
    0.09
    Activations Density 0.078%

    No Known Activations