© 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. 90986
    Prev
    Next
    INDEX
    Explanations

    lightly or lightweight

    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
     lights
    -0.12
    aad
    -0.10
     brightness
    -0.10
    lights
    -0.10
    sworth
    -0.09
    lug
    -0.09
     Lights
    -0.09
    adesh
    -0.09
     halves
    -0.09
     pronto
    -0.08
    POSITIVE LOGITS
    -touch
    0.17
    -duty
    0.16
    -hearted
    0.15
    -weight
    0.15
    weights
    0.14
     touches
    0.14
    ening
    0.14
    est
    0.14
     (<
    0.13
    ened
    0.13
    Activations Density 0.013%

    No Known Activations