© 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. 114785
    Prev
    Next
    INDEX
    Explanations

    names starting with Seth

    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
    ONS
    -0.10
     unp
    -0.10
    tte
    -0.10
    tons
    -0.10
    anzi
    -0.09
    ading
    -0.09
     overcome
    -0.09
     unle
    -0.09
     intense
    -0.09
     peripheral
    -0.09
    POSITIVE LOGITS
    lehem
    0.11
    ereal
    0.10
    esda
    0.10
    unar
    0.10
    .UnitTesting
    0.09
     lesser
    0.09
    BITS
    0.09
    vak
    0.09
    rlen
    0.08
    unya
    0.08
    Activations Density 0.031%

    No Known Activations