© 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. 117076
    Prev
    Next
    INDEX
    Explanations

    names ending in a, e, or y

    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
    .part
    -0.11
     Sammy
    -0.11
     Shed
    -0.11
     aun
    -0.11
    upe
    -0.11
     foe
    -0.11
    esson
    -0.11
    CTL
    -0.11
    isChecked
    -0.11
     roma
    -0.11
    POSITIVE LOGITS
     impro
    0.08
     Capt
    0.07
     recent
    0.06
    izz
    0.06
     Chron
    0.06
    arella
    0.06
    leta
    0.06
     disclosure
    0.06
     provocative
    0.06
     longstanding
    0.06
    Activations Density 0.040%

    No Known Activations