© 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. 91437
    Prev
    Next
    INDEX
    Explanations

    about me / about us

    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
     Gow
    -0.10
    ATAB
    -0.10
    Č↵
    -0.10
    )did
    -0.10
     Roose
    -0.10
     Harding
    -0.10
     [=
    -0.10
     pap
    -0.10
    /Linux
    -0.10
     inbox
    -0.10
    POSITIVE LOGITS
     flashing
    0.09
    shal
    0.09
    porto
    0.08
    About
    0.08
     âĢ¦
    0.08
    ilen
    0.08
    agal
    0.08
     assort
    0.08
     SWAT
    0.07
    agens
    0.07
    Activations Density 0.003%

    No Known Activations