© 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. 114914
    Prev
    Next
    INDEX
    Explanations

    metalloproteinase or metallothionein

    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
     Hear
    -0.10
     plain
    -0.10
    plain
    -0.10
    arat
    -0.10
    ety
    -0.09
    -repeat
    -0.09
     Plain
    -0.08
     Whale
    -0.08
     Trusted
    -0.08
    elin
    -0.08
    POSITIVE LOGITS
    licity
    0.24
    lica
    0.23
    anguage
    0.21
    loid
    0.19
    lic
    0.19
    urgical
    0.18
    working
    0.18
    urgy
    0.18
    lo
    0.17
    lope
    0.16
    Activations Density 0.097%

    No Known Activations