© 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. 30843
    Prev
    Next
    INDEX
    Explanations

    professional outcomes and qualities

    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
    coc
    -0.10
    ilst
    -0.10
     Leer
    -0.09
    mk
    -0.09
    Triple
    -0.09
     extrav
    -0.09
    (div
    -0.09
    dlg
    -0.09
    peg
    -0.09
    antee
    -0.09
    POSITIVE LOGITS
     biting
    0.10
    EB
    0.10
     nond
    0.09
    )”
    0.08
     bite
    0.08
     comer
    0.08
     challenger
    0.08
     contentious
    0.08
    ardless
    0.08
    ):\
    0.08
    Activations Density 0.335%

    No Known Activations