© 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. 91696
    Prev
    Next
    INDEX
    Explanations

    ready for the next step

    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
    ras
    -0.10
    ENN
    -0.10
     hope
    -0.10
    gne
    -0.10
    bor
    -0.09
    erin
    -0.09
     Clayton
    -0.09
     lemon
    -0.09
    ansa
    -0.09
    aku
    -0.09
    POSITIVE LOGITS
     readiness
    0.51
     ready
    0.48
     Ready
    0.44
    ready
    0.39
    Ready
    0.36
    -ready
    0.36
     READY
    0.35
     premature
    0.29
     maturity
    0.29
    _ready
    0.27
    Activations Density 0.111%

    No Known Activations