© 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. 31111
    Prev
    Next
    INDEX
    Explanations

    hits and strikes

    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
    [ind
    -0.09
    pter
    -0.09
     val
    -0.09
    ÑĥÑİ
    -0.09
     segue
    -0.09
    erval
    -0.09
    ientes
    -0.09
    machine
    -0.09
    udad
    -0.09
    developers
    -0.09
    POSITIVE LOGITS
     misses
    0.12
    åĩ»
    0.10
     hits
    0.10
     Hit
    0.09
     strikes
    0.09
     Hits
    0.09
     strike
    0.09
     strokes
    0.09
    .Hit
    0.09
     prostit
    0.08
    Activations Density 0.141%

    No Known Activations