© 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. 88326
    Prev
    Next
    INDEX
    Explanations

    citation following numbers

    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
     autob
    -0.08
     outr
    -0.08
    _nsec
    -0.08
     inf
    -0.07
     bog
    -0.07
     Closet
    -0.07
    neau
    -0.07
    neh
    -0.07
     fl
    -0.06
    ocs
    -0.06
    POSITIVE LOGITS
    (V
    0.32
    ,V
    0.29
    [V
    0.29
    /V
    0.28
     VF
    0.26
    VV
    0.26
     VN
    0.25
     GV
    0.25
     VG
    0.25
     VX
    0.25
    Activations Density 2.727%

    No Known Activations