© 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. 117267
    Prev
    Next
    INDEX
    Explanations

    now or up or min or x or in or ups or before or R

    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
     unc
    -0.08
    [d
    -0.08
    eren
    -0.07
     Koch
    -0.07
    WO
    -0.07
     Amanda
    -0.07
     Rab
    -0.07
    elsen
    -0.07
     outright
    -0.07
     retr
    -0.07
    POSITIVE LOGITS
    avana
    0.13
    aina
    0.11
    igin
    0.10
     Cata
    0.10
    izio
    0.10
     thru
    0.10
    Bloc
    0.09
     scor
    0.09
     curtain
    0.09
    _qs
    0.09
    Activations Density 0.184%

    No Known Activations