© 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. 50223
    Prev
    Next
    INDEX
    Explanations

    You or him

    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
    ular
    -0.09
     Hancock
    -0.08
    aram
    -0.08
    oni
    -0.08
     wid
    -0.08
     checksum
    -0.08
    .Cloud
    -0.08
     agility
    -0.08
     grim
    -0.08
     Denis
    -0.08
    POSITIVE LOGITS
     him
    0.24
     he
    0.22
     she
    0.21
    ä»ĸ
    0.21
     his
    0.20
    —he
    0.19
    him
    0.18
    gnore
    0.18
     her
    0.18
    å¥
    0.17
    Activations Density 0.129%

    No Known Activations