© 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. 113548
    Prev
    Next
    INDEX
    Explanations

    plural and noun suffixes

    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
    s
    -0.13
    en
    -0.12
    aar
    -0.12
    enk
    -0.11
    alles
    -0.11
    enor
    -0.11
    ing
    -0.11
    #ab
    -0.10
    eneg
    -0.10
    /assert
    -0.10
    POSITIVE LOGITS
    ÑģÑı
    0.11
    jo
    0.09
    ble
    0.08
    ives
    0.08
    bies
    0.08
    ves
    0.07
    rah
    0.07
    Âł
    0.07
    BLE
    0.07
    yl
    0.07
    Activations Density 1.387%

    No Known Activations