© 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. 88625
    Prev
    Next
    INDEX
    Explanations

    any/ever variations

    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
     neither
    -0.14
     almost
    -0.12
     none
    -0.12
     very
    -0.11
     surprisingly
    -0.11
     evidently
    -0.10
     VERY
    -0.10
    very
    -0.10
    almost
    -0.10
     thankfully
    -0.10
    POSITIVE LOGITS
     anything
    0.39
    anything
    0.32
     ever
    0.29
     anywhere
    0.29
     Anything
    0.28
     any
    0.28
     EVER
    0.28
    Anything
    0.27
     ANY
    0.24
     remotely
    0.24
    Activations Density 0.234%

    No Known Activations