© 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. 90286
    Prev
    Next
    INDEX
    Explanations

    pronouns and verbs indicating direction or possession

    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
    erb
    -0.11
     Cout
    -0.10
    dre
    -0.10
     Encyclopedia
    -0.09
     Tag
    -0.09
    anter
    -0.09
     freedoms
    -0.09
    ITES
    -0.09
    blink
    -0.09
     bark
    -0.09
    POSITIVE LOGITS
     own
    0.12
    ervo
    0.09
    jen
    0.09
     forcefully
    0.09
     force
    0.09
    izon
    0.09
    /by
    0.09
     forcibly
    0.09
     pallet
    0.08
     indem
    0.08
    Activations Density 0.009%

    No Known Activations