© 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. 49931
    Prev
    Next
    INDEX
    Explanations

    timing of events

    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
     respectively
    -0.11
     semif
    -0.10
    rov
    -0.09
    lite
    -0.09
    ика
    -0.09
     relent
    -0.09
    aque
    -0.09
    sic
    -0.09
    PID
    -0.09
    utto
    -0.09
    POSITIVE LOGITS
    aub
    0.09
    isters
    0.09
    zi
    0.08
    ihan
    0.08
    RP
    0.08
    åĪĻ
    0.07
    abo
    0.07
    ait
    0.07
     Smy
    0.07
    oken
    0.07
    Activations Density 0.284%

    No Known Activations