© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 32223
    Prev
    Next
    INDEX
    Explanations

    functioning of

    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
     alternate
    -0.10
     Alternate
    -0.10
    uos
    -0.10
     lett
    -0.09
    UIS
    -0.09
    'em
    -0.09
    elman
    -0.09
     Peterson
    -0.09
     Sco
    -0.09
    /rem
    -0.09
    POSITIVE LOGITS
    bab
    0.10
     bu
    0.09
    озв
    0.09
     bust
    0.08
     Aff
    0.08
    oa
    0.08
     barr
    0.08
    });↵↵↵↵
    0.08
    credits
    0.08
    riel
    0.08
    Activations Density 0.517%

    No Known Activations