© 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. 24935
    Prev
    Next
    INDEX
    Explanations

    solid-phase

    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
     mutil
    -0.10
    nell
    -0.10
    nee
    -0.10
     sensit
    -0.09
    ikt
    -0.09
     Renew
    -0.09
    erm
    -0.09
    vic
    -0.09
     jap
    -0.09
    iniz
    -0.09
    POSITIVE LOGITS
    -solid
    0.25
     solid
    0.23
     Solid
    0.21
    Solid
    0.19
    solid
    0.19
     solidity
    0.17
    .Solid
    0.15
    olid
    0.15
     grounding
    0.15
     dependable
    0.14
    Activations Density 0.073%

    No Known Activations