© 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. 89477
    Prev
    Next
    INDEX
    Explanations

    grandparent terms

    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
     Dy
    -0.09
    mate
    -0.09
    room
    -0.09
    rez
    -0.09
     luck
    -0.08
     DL
    -0.08
    opro
    -0.08
    CID
    -0.08
    anz
    -0.08
    less
    -0.08
    POSITIVE LOGITS
    eur
    0.15
    /gr
    0.12
    eu
    0.10
    chalk
    0.10
    -grand
    0.10
    .Parse
    0.10
    iosity
    0.10
    -aged
    0.09
    edly
    0.09
    -Israel
    0.09
    Activations Density 0.045%

    No Known Activations