© 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. 113493
    Prev
    Next
    INDEX
    Explanations

    suffix "-ized"

    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
    ED
    -0.13
    dale
    -0.11
    idades
    -0.10
    ES
    -0.10
    idor
    -0.10
    ilde
    -0.10
    CED
    -0.10
    adin
    -0.10
    pered
    -0.10
    zyÄĩ
    -0.10
    POSITIVE LOGITS
    ж
    0.20
    iction
    0.19
    ziej
    0.19
    olph
    0.18
    nesday
    0.18
    igital
    0.18
    rive
    0.18
    irect
    0.16
    imensional
    0.16
    entity
    0.16
    Activations Density 2.077%

    No Known Activations