© 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. 49867
    Prev
    Next
    INDEX
    Explanations

    when clauses describing problems

    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
    /of
    -0.11
    ار
    -0.11
    ilo
    -0.10
    acl
    -0.10
    arat
    -0.10
    sher
    -0.10
     {}).
    -0.10
    qt
    -0.10
    abb
    -0.09
    aro
    -0.09
    POSITIVE LOGITS
    ward
    0.10
     questioned
    0.09
    oret
    0.08
    contro
    0.08
     dawn
    0.08
     vez
    0.08
    imension
    0.07
     Walls
    0.07
     faced
    0.07
    conte
    0.07
    Activations Density 0.239%

    No Known Activations