© 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. 112695
    Prev
    Next
    INDEX
    Explanations

    replaced with/by

    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
     replacements
    -0.14
    abox
    -0.12
     replacement
    -0.12
     Replace
    -0.11
     Replacement
    -0.10
     æĽ
    -0.10
    Replace
    -0.10
    replacement
    -0.10
     replaces
    -0.09
     successor
    -0.09
    POSITIVE LOGITS
     by
    0.14
     with
    0.13
    ASM
    0.10
    SYS
    0.10
    ewith
    0.10
    with
    0.09
    edBy
    0.09
    /by
    0.09
    igo
    0.09
    ITHER
    0.09
    Activations Density 0.008%

    No Known Activations