© 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. 50036
    Prev
    Next
    INDEX
    Explanations

    NAMES ending in mir, -ir, -ur

    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
    ners
    -0.13
    umi
    -0.10
    iedo
    -0.10
    conc
    -0.09
    icion
    -0.09
    sert
    -0.09
    eken
    -0.09
     ener
    -0.09
    colo
    -0.09
    ition
    -0.09
    POSITIVE LOGITS
    hos
    0.11
    ing
    0.11
    osate
    0.09
    aho
    0.09
    acle
    0.09
    zia
    0.08
     successive
    0.08
    [block
    0.08
     tying
    0.08
     Gins
    0.08
    Activations Density 0.005%

    No Known Activations