© 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. 91985
    Prev
    Next
    INDEX
    Explanations

    list item separators

    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
    acus
    -0.11
     nós
    -0.11
    clr
    -0.10
     Lig
    -0.10
     anatom
    -0.09
    ufe
    -0.09
    */↵
    -0.09
     paradigm
    -0.09
     syn
    -0.09
     ung
    -0.09
    POSITIVE LOGITS
    gli
    0.08
     Sach
    0.08
    mant
    0.07
    stown
    0.07
    <|fim_middle|>
    0.07
    vault
    0.07
    boxing
    0.07
     vinc
    0.07
     prive
    0.07
     sai
    0.07
    Activations Density 0.139%

    No Known Activations