© 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. 114781
    Prev
    Next
    INDEX
    Explanations

    Cinder, Tinder, Cair, cinnamon

    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
    uset
    -0.10
    cpy
    -0.10
     Omn
    -0.09
    sess
    -0.09
    unch
    -0.09
     noct
    -0.09
    /ex
    -0.09
    reck
    -0.09
    jec
    -0.09
    onomic
    -0.09
    POSITIVE LOGITS
    ella
    0.19
     Cinder
    0.16
    ellas
    0.13
    alla
    0.12
    blocks
    0.12
    block
    0.11
    coal
    0.10
    steel
    0.10
     ashes
    0.10
    abra
    0.10
    Activations Density 0.003%

    No Known Activations