© 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. 49113
    Prev
    Next
    INDEX
    Explanations

    him/them in/on/behind

    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
     voluntarily
    -0.11
     willingly
    -0.11
     attent
    -0.10
     faithfully
    -0.10
     Fon
    -0.09
     brav
    -0.09
     grabs
    -0.09
    amar
    -0.09
     impressed
    -0.09
     composed
    -0.09
    POSITIVE LOGITS
     Send
    0.13
    /send
    0.12
    Send
    0.12
     send
    0.12
     placement
    0.12
     paired
    0.12
     kept
    0.11
     sent
    0.11
     indo
    0.11
     isolated
    0.11
    Activations Density 0.317%

    No Known Activations