© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 4155
    Prev
    Next
    INDEX
    Explanations

    specialized content or complex descriptions

    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
    ,
    -0.09
     —
    -0.07
     in
    -0.07
     at
    -0.06
    .
    -0.06
     –
    -0.06
     as
    -0.06
     and
    -0.06
     for
    -0.06
     Aff
    -0.06
    POSITIVE LOGITS
     descon
    0.13
    Ľå»º
    0.13
    ERSHEY
    0.13
     firstly
    0.12
    endcode
    0.12
     alcuni
    0.12
    >↵↵↵
    0.12
    {lng
    0.12
    -valu
    0.12
    timeofday
    0.12
    Activations Density 1.355%

    No Known Activations