© 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. 14750
    Prev
    Next
    INDEX
    Explanations

    following someone or something

    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
    uu
    -0.11
    دÙĩ
    -0.09
     pled
    -0.08
    224
    -0.08
    ths
    -0.08
    lesia
    -0.08
     exh
    -0.08
     ratt
    -0.07
    chip
    -0.07
     holland
    -0.07
    POSITIVE LOGITS
     ours
    0.16
     yours
    0.13
     ourselves
    0.12
     RESULT
    0.11
     our
    0.11
    osa
    0.10
     globals
    0.10
    igrams
    0.10
    medi
    0.10
    arb
    0.10
    Activations Density 0.115%

    No Known Activations