© 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. 28365
    Prev
    Next
    INDEX
    Explanations

    you?

    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
    198
    -0.09
     Rocky
    -0.09
    ìĤ¬
    -0.08
     Jah
    -0.08
     Ñģп
    -0.08
    ł
    -0.08
     Cox
    -0.08
    +")
    -0.08
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.08
    ìłģ
    -0.08
    POSITIVE LOGITS
    _you
    0.19
     you
    0.19
    you
    0.15
    -you
    0.15
     You
    0.15
    ä½ł
    0.14
     YOU
    0.13
    You
    0.13
     tou
    0.12
    >You
    0.12
    Activations Density 0.336%

    No Known Activations