© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 111574
    Prev
    Next
    INDEX
    Explanations

    uncertainty or questions

    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
    Negative Logits
     Slater
    -0.11
     uncont
    -0.10
    ained
    -0.09
    nect
    -0.09
    acket
    -0.09
    gom
    -0.09
     Sens
    -0.08
    anean
    -0.08
     Nash
    -0.08
     punishable
    -0.08
    POSITIVE LOGITS
     dun
    0.31
     Dun
    0.28
     Beats
    0.26
     unknown
    0.26
     Unknown
    0.24
     unsure
    0.22
    Unknown
    0.21
     unclear
    0.21
    unknown
    0.20
     beats
    0.20
    Activations Density 0.147%

    No Known Activations