© 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. 113472
    Prev
    Next
    INDEX
    Explanations

    words ending in 'al' or 'ational'

    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
    ally
    -0.16
    ality
    -0.12
    alse
    -0.11
    ALLY
    -0.11
    NESS
    -0.10
    ãĥ¼ãĥ«
    -0.10
    LY
    -0.09
    759
    -0.09
    urs
    -0.09
    .Cursor
    -0.09
    POSITIVE LOGITS
     psychology
    0.12
    æij
    0.11
     psychologist
    0.10
    -functional
    0.10
     chemistry
    0.10
    /setup
    0.09
    umen
    0.09
     electrom
    0.09
    iness
    0.09
     videos
    0.09
    Activations Density 0.448%

    No Known Activations