© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 6230
    Prev
    Next
    INDEX
    Explanations

    benefit for me

    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
    izada
    -0.14
    iae
    -0.12
    zej
    -0.12
     snapping
    -0.12
     Fres
    -0.12
    HN
    -0.11
    orial
    -0.11
    adt
    -0.11
    584
    -0.11
     Hansen
    -0.11
    POSITIVE LOGITS
     coping
    0.08
     Voy
    0.08
     hoped
    0.07
     ultimately
    0.07
     lamb
    0.07
     Hil
    0.07
     hopeful
    0.07
    725
    0.07
     hopes
    0.07
     reap
    0.07
    Activations Density 0.125%

    No Known Activations