© 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. 50909
    Prev
    Next
    INDEX
    Explanations

    frozen state or freezing

    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
     cient
    -0.10
    monic
    -0.10
    sein
    -0.09
    nop
    -0.09
    monds
    -0.09
    woo
    -0.09
     hottest
    -0.09
    clo
    -0.09
     begr
    -0.09
    ForRow
    -0.09
    POSITIVE LOGITS
    -frame
    0.14
    /th
    0.12
    zet
    0.11
    -solid
    0.11
     stiff
    0.10
     thaw
    0.10
     yogurt
    0.09
     framed
    0.09
    haps
    0.09
    punk
    0.09
    Activations Density 0.026%

    No Known Activations