© 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. 33070
    Prev
    Next
    INDEX
    Explanations

    negative aspects or context

    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
    sig
    -0.13
    kie
    -0.11
    stalk
    -0.11
    mur
    -0.11
     Tac
    -0.11
     chooser
    -0.11
    arez
    -0.10
    ackbar
    -0.10
     [.
    -0.10
    oner
    -0.10
    POSITIVE LOGITS
     involving
    0.11
     with
    0.10
     amidst
    0.09
     combining
    0.08
     indoors
    0.08
     Bened
    0.08
    ihn
    0.08
     including
    0.08
     while
    0.08
    vsp
    0.08
    Activations Density 0.001%

    No Known Activations