© 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. 16911
    Prev
    Next
    INDEX
    Explanations

    demonstrative pronouns

    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
     putt
    -0.11
     ?:
    -0.10
    Ñĥж
    -0.10
    ONGL
    -0.10
    .delivery
    -0.10
    hol
    -0.09
    ÑĤÑĮ
    -0.09
     undercover
    -0.09
     Gratuit
    -0.09
     wa
    -0.09
    POSITIVE LOGITS
     fact
    0.14
     aspect
    0.12
     circumstance
    0.10
     FACT
    0.10
     minor
    0.10
     possibility
    0.09
    hev
    0.09
     assumption
    0.09
    115
    0.09
     prestigious
    0.09
    Activations Density 0.107%

    No Known Activations