© 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. 114376
    Prev
    Next
    INDEX
    Explanations

    Terry followed by a surname

    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
     Vit
    -0.08
    ity
    -0.08
    eni
    -0.08
     sneak
    -0.08
     bodies
    -0.08
     body
    -0.08
     distinct
    -0.07
     spacing
    -0.07
     vit
    -0.07
     Jou
    -0.07
    POSITIVE LOGITS
    <<<
    0.12
    eo
    0.12
    apt
    0.12
    /sm
    0.11
    _insn
    0.11
    elay
    0.11
    apter
    0.11
     conveying
    0.10
    =User
    0.10
    è¾ij
    0.10
    Activations Density 0.004%

    No Known Activations