© 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. 15928
    Prev
    Next
    INDEX
    Explanations

    -ers / -mers endings

    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
    sey
    -0.12
    ç©
    -0.10
    ropy
    -0.10
    eca
    -0.10
    than
    -0.10
    liest
    -0.09
    ion
    -0.09
    ANCH
    -0.09
    nten
    -0.08
     restr
    -0.08
    POSITIVE LOGITS
    s
    0.36
    hip
    0.20
    hips
    0.19
    sand
    0.17
    hed
    0.17
    ohn
    0.16
    sen
    0.16
    hots
    0.16
    o
    0.16
    sheets
    0.15
    Activations Density 0.303%

    No Known Activations