© 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. 91020
    Prev
    Next
    INDEX
    Explanations

    Lamborghini

    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
     nest
    -0.11
     nests
    -0.10
    zel
    -0.09
    utomation
    -0.09
     ident
    -0.09
     dign
    -0.09
    ihat
    -0.09
    icho
    -0.09
    rvine
    -0.09
     Pom
    -0.08
    POSITIVE LOGITS
     Chop
    0.10
    ropa
    0.10
     butter
    0.10
     chop
    0.10
    è´
    0.09
     lamb
    0.09
    orghini
    0.09
    iot
    0.09
    rop
    0.09
    das
    0.09
    Activations Density 0.007%

    No Known Activations