© 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. 17392
    Prev
    Next
    INDEX
    Explanations

    replace in text

    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
    apus
    -0.09
     Dew
    -0.08
    hit
    -0.08
    hole
    -0.08
    isan
    -0.08
     alternative
    -0.08
     invers
    -0.07
    Squared
    -0.07
    ORS
    -0.07
    149
    -0.07
    POSITIVE LOGITS
    /add
    0.17
    able
    0.16
    /up
    0.14
    /update
    0.13
    /en
    0.12
    /sub
    0.11
    unan
    0.11
    /ext
    0.11
    enia
    0.10
    /new
    0.10
    Activations Density 0.045%

    No Known Activations