© 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. 116872
    Prev
    Next
    INDEX
    Explanations

    wrote about

    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
     writing
    -0.14
    writing
    -0.13
    ror
    -0.12
     writings
    -0.11
    /random
    -0.11
     Writing
    -0.11
    ogi
    -0.11
    Writing
    -0.10
     Mais
    -0.10
    uent
    -0.10
    POSITIVE LOGITS
     down
    0.19
     about
    0.18
    about
    0.15
     ABOUT
    0.12
    acher
    0.12
    -down
    0.12
    down
    0.11
    .about
    0.11
     About
    0.11
     Down
    0.10
    Activations Density 0.100%

    No Known Activations