© 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. 115801
    Prev
    Next
    INDEX
    Explanations

    "lines"

    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
     thanking
    -0.12
     urgently
    -0.12
    yte
    -0.11
    lug
    -0.11
     accompanied
    -0.11
     relaxed
    -0.11
    577
    -0.10
    ewe
    -0.10
    gor
    -0.10
    pressed
    -0.10
    POSITIVE LOGITS
     Wrath
    0.07
    lier
    0.07
    olin
    0.07
     Bil
    0.07
     Hast
    0.06
    lian
    0.06
     Aggregate
    0.06
     Ai
    0.06
    omer
    0.06
    .ali
    0.06
    Activations Density 0.479%

    No Known Activations