© 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. 91400
    Prev
    Next
    INDEX
    Explanations

    play a role

    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
     differently
    -0.13
    举
    -0.13
     stuff
    -0.11
     negativity
    -0.11
    uen
    -0.11
     cyl
    -0.11
    олÑı
    -0.11
    thing
    -0.11
    things
    -0.11
    frag
    -0.10
    POSITIVE LOGITS
     certain
    0.09
     a
    0.09
     multiple
    0.08
     different
    0.08
     some
    0.08
     another
    0.08
    nish
    0.07
     whatever
    0.07
     various
    0.07
     any
    0.07
    Activations Density 0.417%

    No Known Activations