© 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. 89556
    Prev
    Next
    INDEX
    Explanations

    end of phrase

    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
     convers
    -0.09
     pied
    -0.09
     altern
    -0.09
     Conversely
    -0.08
     Statue
    -0.08
     alternatively
    -0.08
    setData
    -0.08
     moreover
    -0.08
     bart
    -0.08
    aber
    -0.08
    POSITIVE LOGITS
     surely
    0.14
     clearly
    0.13
     ultimately
    0.12
     acknow
    0.12
     whether
    0.11
    whether
    0.11
     remember
    0.10
    ult
    0.10
    356
    0.10
    ITT
    0.10
    Activations Density 0.027%

    No Known Activations