© 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. 17500
    Prev
    Next
    INDEX
    Explanations

    prepositions and postpositions

    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
    phas
    -0.08
    arel
    -0.08
    Trap
    -0.08
    rys
    -0.08
    chk
    -0.08
    IO
    -0.07
    frm
    -0.07
     Thief
    -0.07
    ef
    -0.07
    eye
    -0.07
    POSITIVE LOGITS
    /at
    0.17
    /from
    0.13
    /on
    0.13
    /by
    0.12
    /as
    0.11
    ADOR
    0.11
    /back
    0.11
    /in
    0.11
    /to
    0.10
    /of
    0.10
    Activations Density 0.744%

    No Known Activations