© 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. 17807
    Prev
    Next
    INDEX
    Explanations

    best of both worlds and styles

    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
     paired
    -0.09
     identical
    -0.09
    orc
    -0.08
    inson
    -0.08
    orney
    -0.08
    oppel
    -0.08
     instrumental
    -0.07
     UNESCO
    -0.07
     Duo
    -0.07
     MSR
    -0.07
    POSITIVE LOGITS
     elements
    0.22
     influences
    0.20
     worlds
    0.19
     hybrid
    0.19
     combines
    0.18
     combine
    0.17
     styles
    0.17
     combining
    0.17
    elements
    0.17
     extremes
    0.16
    Activations Density 0.267%

    No Known Activations