© 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. 16333
    Prev
    Next
    INDEX
    Explanations

    individual attributes

    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
    /Runtime
    -0.11
    reinterpret
    -0.11
    /manage
    -0.10
     elaborate
    -0.10
     fools
    -0.10
    AVOR
    -0.10
     reperc
    -0.10
    łí
    -0.10
    rio
    -0.10
     Impl
    -0.10
    POSITIVE LOGITS
     behavior
    0.18
     personality
    0.17
     existence
    0.17
     abilities
    0.17
     status
    0.17
     nature
    0.17
     identity
    0.16
     appearance
    0.16
     role
    0.15
     presence
    0.15
    Activations Density 0.293%

    No Known Activations