© 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. 31805
    Prev
    Next
    INDEX
    Explanations

    cannot hold

    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
     myself
    -0.08
     HB
    -0.08
     Hear
    -0.08
    ubo
    -0.07
    GI
    -0.07
    itti
    -0.07
     bile
    -0.07
     col
    -0.07
    557
    -0.07
    —I
    -0.07
    POSITIVE LOGITS
     believes
    0.12
     initially
    0.12
     expects
    0.12
    /english
    0.11
     expected
    0.11
     hesitate
    0.11
     believe
    0.10
     seems
    0.10
    kip
    0.10
    lad
    0.10
    Activations Density 0.045%

    No Known Activations