© 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. 91088
    Prev
    Next
    INDEX
    Explanations

    eb/EB

    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
     Rough
    -0.11
    SPACE
    -0.10
     Hamp
    -0.10
    OMPI
    -0.10
    nces
    -0.10
     stake
    -0.10
    rng
    -0.10
    isters
    -0.10
    ord
    -0.10
     Trouble
    -0.10
    POSITIVE LOGITS
     ev
    0.09
    lish
    0.08
    hel
    0.08
    dbg
    0.08
    ony
    0.08
     Ev
    0.08
     Suz
    0.07
     forget
    0.07
    ti
    0.07
     obscure
    0.07
    Activations Density 0.005%

    No Known Activations