© 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. 116556
    Prev
    Next
    INDEX
    Explanations

    a [quantity/specific item]

    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
     surprisingly
    -0.11
     Kb
    -0.10
     tendency
    -0.10
     sparse
    -0.10
    eros
    -0.10
    andes
    -0.10
    ADI
    -0.10
    sharp
    -0.10
     strangely
    -0.10
    /downloads
    -0.09
    POSITIVE LOGITS
     little
    0.13
     special
    0.13
     bit
    0.12
     few
    0.11
     wee
    0.11
     some
    0.10
     different
    0.10
     compr
    0.10
     proper
    0.10
     SPECIAL
    0.09
    Activations Density 0.117%

    No Known Activations