© 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. 115211
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and articles

    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
     erst
    -0.09
     realised
    -0.08
     ‘
    -0.08
     supposed
    -0.08
     «
    -0.07
     Rahman
    -0.07
     vis
    -0.07
     wich
    -0.07
     Ross
    -0.07
     decidedly
    -0.07
    POSITIVE LOGITS
     trending
    0.13
     carg
    0.12
    esus
    0.12
     Lov
    0.12
    cka
    0.12
    ifr
    0.12
     cuer
    0.11
    CardBody
    0.11
    quo
    0.11
    )("
    0.11
    Activations Density 0.087%

    No Known Activations