© 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. 28932
    Prev
    Next
    INDEX
    Explanations

    what's the equivalent

    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
     Tap
    -0.10
    uti
    -0.10
    sten
    -0.10
     Parm
    -0.10
    uchi
    -0.09
     <$
    -0.09
     Budd
    -0.09
     bitter
    -0.09
    rar
    -0.09
     tapping
    -0.09
    POSITIVE LOGITS
    wg
    0.09
     Higgins
    0.09
    onian
    0.08
    anko
    0.08
    RON
    0.08
     fifo
    0.08
    enso
    0.08
    ifs
    0.08
    ellas
    0.08
     Adult
    0.08
    Activations Density 0.002%

    No Known Activations