© 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. 29917
    Prev
    Next
    INDEX
    Explanations

    all, each, every, any

    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
     Everywhere
    -0.14
     everywhere
    -0.14
     various
    -0.14
    äºĽ
    -0.13
    both
    -0.13
     Various
    -0.13
     both
    -0.13
     fewer
    -0.12
     several
    -0.12
    -many
    -0.12
    POSITIVE LOGITS
     anyone
    0.09
     anybody
    0.09
     any
    0.07
    aza
    0.07
     blatant
    0.07
    anter
    0.07
     Fs
    0.06
     neigh
    0.06
     Baghd
    0.06
    yal
    0.06
    Activations Density 0.407%

    No Known Activations