© 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. 16604
    Prev
    Next
    INDEX
    Explanations

    Chile and words starting with 'ir' or 'ad'

    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
     chances
    -0.14
    charge
    -0.13
    /change
    -0.12
     chance
    -0.12
    ossa
    -0.12
     sincer
    -0.11
    -China
    -0.11
    chapter
    -0.11
    ×Ĺ
    -0.11
     charge
    -0.10
    POSITIVE LOGITS
    lain
    0.18
    apeake
    0.14
    icles
    0.12
    ographed
    0.12
    sterol
    0.12
    icle
    0.11
    reuse
    0.11
    isty
    0.11
    strap
    0.11
    acter
    0.10
    Activations Density 0.962%

    No Known Activations