© 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. 33618
    Prev
    Next
    INDEX
    Explanations

    "searched for", "error in", "play the", "win or", "are here"

    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
     your
    -0.13
    ä½ł
    -0.12
     you
    -0.11
    your
    -0.11
     yourself
    -0.10
     civ
    -0.09
     YOUR
    -0.09
     YOU
    -0.09
    urls
    -0.09
    UV
    -0.09
    POSITIVE LOGITS
     Emm
    0.10
     Legacy
    0.10
     maté
    0.10
    alc
    0.10
     zich
    0.09
    _perms
    0.09
     vé
    0.09
     emulation
    0.09
     rever
    0.09
    ullo
    0.09
    Activations Density 0.249%

    No Known Activations