© 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. 29867
    Prev
    Next
    INDEX
    Explanations

    ward off

    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
     impart
    -0.10
    zar
    -0.10
     overlays
    -0.09
    Particles
    -0.09
     Rapids
    -0.09
    hora
    -0.09
     flourish
    -0.09
    edere
    -0.09
     PTS
    -0.09
    velop
    -0.09
    POSITIVE LOGITS
     "><
    0.08
     rem
    0.08
     diss
    0.08
     sod
    0.08
     insult
    0.07
     reli
    0.07
     widely
    0.07
     hail
    0.07
     Permanent
    0.07
     reckon
    0.07
    Activations Density 0.009%

    No Known Activations