© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 30249
    Prev
    Next
    INDEX
    Explanations

    numerical citations in brackets

    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
    aal
    -0.11
    uteur
    -0.08
    iene
    -0.08
    <strong
    -0.08
     sims
    -0.08
    aan
    -0.08
    adera
    -0.07
    ä½Ļ
    -0.07
     seemingly
    -0.07
    .buttons
    -0.07
    POSITIVE LOGITS
    nb
    0.14
    sic
    0.12
     Bord
    0.11
     citation
    0.11
     PW
    0.11
    clar
    0.11
    notes
    0.11
    verification
    0.11
    citation
    0.10
     pear
    0.10
    Activations Density 0.040%

    No Known Activations