© 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. 29104
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
     Handler
    -0.09
    alom
    -0.09
    exas
    -0.09
     Massive
    -0.09
     Conor
    -0.09
     Pharma
    -0.09
     Heller
    -0.09
    /Edit
    -0.09
    ouble
    -0.08
    temps
    -0.08
    POSITIVE LOGITS
     —
    0.11
    elia
    0.11
     [âĢ¦
    0.10
     extrem
    0.10
    [âĢ¦]
    0.10
    _constants
    0.09
     Guill
    0.09
     âĶľâĶĢâĶĢ
    0.09
     shall
    0.09
     sue
    0.09
    Activations Density 0.256%

    No Known Activations