© 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. 5177
    Prev
    Next
    INDEX
    Explanations

    words after list separators

    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
    rei
    -0.12
    ania
    -0.11
     Zac
    -0.10
     [âĢ¦]↵↵
    -0.10
    âĢIJ
    -0.10
     nearest
    -0.10
     oi
    -0.10
     UIS
    -0.10
    Kin
    -0.10
     sui
    -0.10
    POSITIVE LOGITS
    --
    0.12
    "--
    0.10
    ...
    0.08
     _
    0.07
    uke
    0.07
     Hy
    0.07
    zew
    0.07
    /I
    0.07
     FS
    0.07
     Fifth
    0.07
    Activations Density 0.276%

    No Known Activations