© 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. 26141
    Prev
    Next
    INDEX
    Explanations

    effective and related suffixes

    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
     effected
    -0.12
    Effects
    -0.10
    edException
    -0.09
    .makeText
    -0.09
    wear
    -0.09
     effects
    -0.09
    enko
    -0.09
    erable
    -0.09
     Effects
    -0.09
     successes
    -0.09
    POSITIVE LOGITS
    æŀľ
    0.25
    çİĩ
    0.18
    ively
    0.15
    iveness
    0.12
     altru
    0.12
    alley
    0.12
    uating
    0.12
    /product
    0.12
    uate
    0.12
     communication
    0.11
    Activations Density 0.123%

    No Known Activations