© 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. 48217
    Prev
    Next
    INDEX
    Explanations

    preposition followed by pronoun

    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
    CESS
    -0.08
    .cgi
    -0.08
    AC
    -0.08
    osto
    -0.08
     dew
    -0.08
     Alb
    -0.07
    volt
    -0.07
    CK
    -0.07
    fad
    -0.07
     ins
    -0.07
    POSITIVE LOGITS
     them
    0.12
     themselves
    0.12
     its
    0.12
     Grove
    0.11
     ihr
    0.11
    aty
    0.11
    alin
    0.10
    ère
    0.10
     herself
    0.10
    pired
    0.10
    Activations Density 0.219%

    No Known Activations