© 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. 50625
    Prev
    Next
    INDEX
    Explanations

    won’t

    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
    ADS
    -0.12
    iner
    -0.12
    aus
    -0.11
     Typed
    -0.11
     Salah
    -0.11
    oron
    -0.11
    (public
    -0.10
    endif
    -0.10
    лем
    -0.10
    iangle
    -0.10
    POSITIVE LOGITS
    't
    0.13
    ’t
    0.13
     tickets
    0.10
    ked
    0.08
    ict
    0.08
     lottery
    0.08
    emon
    0.07
    rens
    0.07
    ically
    0.07
    ot
    0.07
    Activations Density 0.012%

    No Known Activations