© 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. 31445
    Prev
    Next
    INDEX
    Explanations

    licensed subject terms

    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
     were
    -0.15
    were
    -0.14
     Were
    -0.13
    rael
    -0.13
    Were
    -0.13
     are
    -0.12
     weren
    -0.11
    eldo
    -0.10
    _are
    -0.10
    elf
    -0.10
    POSITIVE LOGITS
    edor
    0.11
    ally
    0.10
    ardon
    0.09
    ed
    0.08
     was
    0.08
    tt
    0.08
    val
    0.08
    eda
    0.08
    ly
    0.08
    urrect
    0.08
    Activations Density 0.090%

    No Known Activations