© 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. 113267
    Prev
    Next
    INDEX
    Explanations

    Moise, Mo, Moxiecode

    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
    erton
    -0.11
     orientation
    -0.10
     orient
    -0.09
    ohl
    -0.09
    (SP
    -0.09
    Risk
    -0.08
     Orientation
    -0.08
     Activ
    -0.08
    orientation
    -0.08
     activates
    -0.08
    POSITIVE LOGITS
     mo
    0.11
     Mo
    0.10
    {_
    0.10
    /target
    0.10
     Fach
    0.10
    defs
    0.10
    dre
    0.09
    ambique
    0.09
    aten
    0.09
     desperate
    0.09
    Activations Density 0.052%

    No Known Activations