© 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. 32070
    Prev
    Next
    INDEX
    Explanations

    access, updates, notices, gallery, code

    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
     gst
    -0.10
    evil
    -0.10
    _gas
    -0.10
    erde
    -0.10
    ãĤ¤ãĥĪ
    -0.10
     Dexter
    -0.09
    .wr
    -0.09
     voyeur
    -0.09
    ighbor
    -0.09
     motel
    -0.09
    POSITIVE LOGITS
     Tib
    0.09
    adas
    0.08
     Edition
    0.08
    ledo
    0.08
    sis
    0.08
    ensis
    0.08
    ron
    0.08
     Inv
    0.07
    mez
    0.07
     lé
    0.07
    Activations Density 2.329%

    No Known Activations