© 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. 113834
    Prev
    Next
    INDEX
    Explanations

    well as

    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
    jt
    -0.11
    Mill
    -0.11
     daylight
    -0.10
    ï¸ı
    -0.10
    mill
    -0.10
    zp
    -0.10
    pis
    -0.10
     Mill
    -0.10
     Klein
    -0.10
    ric
    -0.10
    POSITIVE LOGITS
     as
    0.16
    -known
    0.12
     Corvette
    0.08
     als
    0.08
     Schl
    0.08
     sebagai
    0.08
    uv
    0.08
     Funk
    0.08
    inda
    0.07
    åıĬ
    0.07
    Activations Density 0.054%

    No Known Activations