© 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. 26915
    Prev
    Next
    INDEX
    Explanations

    content published

    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
     Hor
    -0.09
     Multimedia
    -0.09
     Thur
    -0.08
    -minded
    -0.08
     hor
    -0.08
     gib
    -0.08
     Ko
    -0.08
    Content
    -0.08
    ROL
    -0.07
    LB
    -0.07
    POSITIVE LOGITS
    bia
    0.11
     catast
    0.11
     Favor
    0.10
     favored
    0.10
    ions
    0.10
     favoured
    0.10
    aine
    0.10
     stern
    0.10
    reten
    0.10
    enci
    0.10
    Activations Density 0.028%

    No Known Activations