© 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. 27817
    Prev
    Next
    INDEX
    Explanations

    foot of / foot notes

    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
    plier
    -0.12
    eyed
    -0.11
    mlink
    -0.11
    inner
    -0.11
    ignon
    -0.11
    OST
    -0.11
    ighter
    -0.11
    ét
    -0.11
    Ñİ
    -0.11
    /mac
    -0.10
    POSITIVE LOGITS
    (bottom
    0.08
    notes
    0.08
     pedals
    0.08
     opposite
    0.08
    /top
    0.08
    lights
    0.07
     Wig
    0.07
     accents
    0.07
     Lam
    0.07
     cams
    0.07
    Activations Density 0.003%

    No Known Activations