© 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. 49083
    Prev
    Next
    INDEX
    Explanations

    words following "in"

    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
     bidding
    -0.09
    adem
    -0.09
     Mish
    -0.09
    ocity
    -0.09
    aldo
    -0.09
    erval
    -0.09
    chas
    -0.09
    åķĨ
    -0.09
     fin
    -0.09
     lanc
    -0.09
    POSITIVE LOGITS
     SV
    0.10
    iven
    0.09
     Nach
    0.09
     Stanton
    0.09
     Frog
    0.09
     Fro
    0.09
     FAG
    0.09
     legacy
    0.09
    uniq
    0.09
     transl
    0.08
    Activations Density 0.005%

    No Known Activations