© 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. 88689
    Prev
    Next
    INDEX
    Explanations

    plot or narrative content

    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
     Sle
    -0.08
     Fot
    -0.07
    otr
    -0.07
     Evidence
    -0.07
    pd
    -0.07
     interfer
    -0.07
     explanatory
    -0.07
    sov
    -0.07
    III
    -0.07
     wording
    -0.07
    POSITIVE LOGITS
     follows
    0.29
     revolves
    0.28
     follow
    0.26
     centers
    0.25
     Follow
    0.24
     protagon
    0.23
     centres
    0.23
    follow
    0.21
     tale
    0.21
     story
    0.21
    Activations Density 0.651%

    No Known Activations