© 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. 6049
    Prev
    Next
    INDEX
    Explanations

    terms and conditions

    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
    aso
    -0.10
     Aub
    -0.09
    macro
    -0.09
     Ups
    -0.09
    geb
    -0.09
     hole
    -0.08
    ROME
    -0.08
    ToF
    -0.08
    unta
    -0.08
    aed
    -0.08
    POSITIVE LOGITS
     conditions
    0.27
    conditions
    0.25
     Conditions
    0.24
    Conditions
    0.22
    _conditions
    0.20
     CONDITIONS
    0.20
     terms
    0.19
    æĿ¡ä»¶
    0.17
    /terms
    0.17
    terms
    0.17
    Activations Density 0.111%

    No Known Activations