© 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. 33122
    Prev
    Next
    INDEX
    Explanations

    Big followed by other words

    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
     Paras
    -0.12
    hof
    -0.11
    iert
    -0.10
    plorer
    -0.10
    hq
    -0.10
    iness
    -0.09
     Norton
    -0.08
     Suff
    -0.08
     Cutting
    -0.08
    ylum
    -0.08
    POSITIVE LOGITS
    gest
    0.14
     Brother
    0.13
    gy
    0.13
    genden
    0.13
    gs
    0.13
    foot
    0.13
    elow
    0.12
    gings
    0.12
    ging
    0.11
    Endian
    0.11
    Activations Density 0.023%

    No Known Activations