© 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. 116085
    Prev
    Next
    INDEX
    Explanations

    eBay, auction, Samsung, AT&T, GitHub

    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
    edb
    -0.09
    aders
    -0.08
    lm
    -0.08
    @a
    -0.08
    coded
    -0.07
    cod
    -0.07
    _"
    -0.07
     Bened
    -0.07
    ems
    -0.07
    cci
    -0.07
    POSITIVE LOGITS
    elle
    0.10
     vs
    0.10
    quirer
    0.10
     stripped
    0.10
    ogle
    0.10
    /banner
    0.09
     spar
    0.09
     Vs
    0.09
    é¦
    0.09
    tur
    0.09
    Activations Density 0.001%

    No Known Activations