© 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. 18209
    Prev
    Next
    INDEX
    Explanations

    match

    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
     Hubb
    -0.09
    hn
    -0.09
    acist
    -0.09
    icher
    -0.09
    ruz
    -0.09
    nage
    -0.09
    pec
    -0.08
     Jens
    -0.08
    usra
    -0.08
    rud
    -0.08
    POSITIVE LOGITS
     match
    0.22
     Match
    0.20
    (match
    0.18
    match
    0.18
     MATCH
    0.17
    stick
    0.17
     matches
    0.16
    -match
    0.16
     matcher
    0.15
    sticks
    0.15
    Activations Density 0.022%

    No Known Activations