© 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. 49610
    Prev
    Next
    INDEX
    Explanations

    information about science and technology

    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
    ifu
    -0.09
     Lambert
    -0.08
     Hanson
    -0.08
     Matte
    -0.07
    Nam
    -0.07
     Chandler
    -0.07
     diz
    -0.07
    avad
    -0.07
    oen
    -0.07
    ardi
    -0.07
    POSITIVE LOGITS
    esan
    0.11
    ASA
    0.11
     Blank
    0.11
     Van
    0.10
    ats
    0.10
    atz
    0.10
     Intervention
    0.10
    abl
    0.10
     uncont
    0.10
    iless
    0.10
    Activations Density 0.058%

    No Known Activations