© 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. 26912
    Prev
    Next
    INDEX
    Explanations

    can/could statements of ability or possibility

    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
     deserved
    -0.10
     Rings
    -0.09
    opher
    -0.08
     renew
    -0.08
    stin
    -0.08
    asil
    -0.08
     illumin
    -0.08
     eas
    -0.08
    izens
    -0.08
     Renew
    -0.08
    POSITIVE LOGITS
     stomach
    0.13
    tol
    0.13
     tolerate
    0.13
     careless
    0.12
     envision
    0.12
    ldr
    0.12
     imagine
    0.12
    imag
    0.11
     convincing
    0.11
     intoler
    0.11
    Activations Density 0.095%

    No Known Activations