© 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. 89183
    Prev
    Next
    INDEX
    Explanations

    words starting with h/f or ending suffix -acy/-ane

    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
    704
    -0.10
     Lub
    -0.10
     impost
    -0.09
    atables
    -0.09
     combust
    -0.09
    ey
    -0.09
    eras
    -0.09
     embarrass
    -0.09
    ixer
    -0.08
     comple
    -0.08
    POSITIVE LOGITS
     owed
    0.11
     enth
    0.10
     Wor
    0.10
     guarante
    0.10
     Fetish
    0.10
    inema
    0.09
    inic
    0.09
    hest
    0.09
    aic
    0.09
    charging
    0.09
    Activations Density 0.001%

    No Known Activations