© 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. 28110
    Prev
    Next
    INDEX
    Explanations

    what better than

    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
    olan
    -0.11
     bolt
    -0.09
    Nota
    -0.09
     cose
    -0.08
    åĥ
    -0.08
     condemned
    -0.08
    azer
    -0.08
    lan
    -0.08
    nar
    -0.08
    lash
    -0.08
    POSITIVE LOGITS
     incomplete
    0.23
     wouldn
    0.23
     obligatory
    0.20
     unavoid
    0.18
     inevitably
    0.17
     cannot
    0.17
     without
    0.17
    Incomplete
    0.17
     rem
    0.16
     Without
    0.16
    Activations Density 0.194%

    No Known Activations