© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 88354
    Prev
    Next
    INDEX
    Explanations

    "here's a" or "here's the"

    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
     Antworten
    -0.10
     Sey
    -0.09
    ours
    -0.09
    hof
    -0.09
    ey
    -0.09
     Stub
    -0.08
    asp
    -0.08
    .tem
    -0.08
    ?key
    -0.08
     pit
    -0.08
    POSITIVE LOGITS
    Ãł
    0.10
    \\\
    0.09
    WWW
    0.09
     prox
    0.09
     divul
    0.09
    statt
    0.09
    lew
    0.09
     Occ
    0.09
     plan
    0.09
     Monkey
    0.08
    Activations Density 0.029%

    No Known Activations