© 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. 49852
    Prev
    Next
    INDEX
    Explanations

    onto, on, to, into, around

    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
     Spears
    -0.11
    uya
    -0.10
    ihn
    -0.10
     youngest
    -0.10
    çīĩ
    -0.10
    dda
    -0.10
    chg
    -0.10
    oho
    -0.10
    aggio
    -0.10
    oice
    -0.10
    POSITIVE LOGITS
     surfaces
    0.14
     someone
    0.12
     whatever
    0.12
     opponent
    0.11
     somebody
    0.11
     whoever
    0.10
     opponents
    0.10
     objects
    0.09
     anything
    0.09
    whatever
    0.09
    Activations Density 0.440%

    No Known Activations