© 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. 116609
    Prev
    Next
    INDEX
    Explanations

    recent past or last time frame

    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
    rat
    -0.10
    rar
    -0.10
    pit
    -0.09
    stand
    -0.09
     Rath
    -0.09
     Rena
    -0.09
     Bail
    -0.09
    PCA
    -0.08
     Sus
    -0.08
    surf
    -0.08
    POSITIVE LOGITS
     recent
    0.19
     recently
    0.18
    recent
    0.16
     last
    0.16
     latest
    0.15
    _recent
    0.15
     Recent
    0.14
     past
    0.13
     Recently
    0.12
    _last
    0.12
    Activations Density 0.336%

    No Known Activations