© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115022
    Prev
    Next
    INDEX
    Explanations

    apache license

    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
     Autonomous
    -0.10
    /apt
    -0.09
     somewhat
    -0.09
     partially
    -0.09
     Spar
    -0.09
     Codec
    -0.09
     arou
    -0.09
     Gallagher
    -0.09
     worth
    -0.08
     Worth
    -0.08
    POSITIVE LOGITS
     silence
    0.14
     shut
    0.14
     Shut
    0.12
     excuses
    0.12
     silenced
    0.12
     Silence
    0.11
    sil
    0.11
    opp
    0.11
     interrupt
    0.11
    pare
    0.10
    Activations Density 0.028%

    No Known Activations