© 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. 50618
    Prev
    Next
    INDEX
    Explanations

    affecting/affected by

    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
    elling
    -0.11
    iers
    -0.10
    ellig
    -0.10
    izable
    -0.10
    isable
    -0.10
     rew
    -0.10
    oning
    -0.10
     rus
    -0.10
    vier
    -0.09
    gger
    -0.09
    POSITIVE LOGITS
    ive
    0.18
    ivity
    0.13
     negatively
    0.13
     adversely
    0.13
    ively
    0.13
     positively
    0.11
    IVE
    0.09
    ations
    0.09
    ected
    0.09
    æŀľ
    0.09
    Activations Density 0.031%

    No Known Activations