© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 112496
    Prev
    Next
    INDEX
    Explanations

    quantifiers of components or examples

    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
    iston
    -0.10
     Stevens
    -0.08
    kest
    -0.08
     frank
    -0.08
    nak
    -0.08
    icip
    -0.08
     underlying
    -0.08
    istes
    -0.07
    apol
    -0.07
     nic
    -0.07
    POSITIVE LOGITS
     коÑĤоÑĢ
    0.16
     consisting
    0.15
     containing
    0.15
     cuales
    0.14
     of
    0.13
     which
    0.13
    which
    0.13
     appearing
    0.13
     belonging
    0.13
     involving
    0.12
    Activations Density 0.128%

    No Known Activations