© 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. 116819
    Prev
    Next
    INDEX
    Explanations

    http strings

    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
    andest
    -0.09
    idak
    -0.08
     Canton
    -0.08
     Laurie
    -0.08
     comple
    -0.07
    chematic
    -0.07
    ashboard
    -0.07
    owers
    -0.07
    arris
    -0.07
    eneric
    -0.07
    POSITIVE LOGITS
     banc
    0.11
     offending
    0.10
    ting
    0.10
    ------↵
    0.10
     thermo
    0.10
    -ton
    0.10
     cle
    0.10
     bo
    0.09
    upy
    0.09
    #####
    0.09
    Activations Density 0.953%

    No Known Activations