© 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. 48533
    Prev
    Next
    INDEX
    Explanations

    http links and Unicode copyright information

    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
    :
    -0.19
    utf
    -0.16
    AAP
    -0.15
    CGPoint
    -0.14
    [[
    -0.14
    block
    -0.13
    CGRect
    -0.13
    -in
    -0.13
    center
    -0.13
    pointer
    -0.13
    POSITIVE LOGITS
    -↵
    0.15
    -↵↵
    0.15
    \↵
    0.12
    -(
    0.12
    *</
    0.10
    ”
    0.10
    *=
    0.10
    __
    0.10
    rolley
    0.10
    innen
    0.09
    Activations Density 0.929%

    No Known Activations