© 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. 114619
    Prev
    Next
    INDEX
    Explanations

    look or looking for

    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
    244
    -0.08
    lc
    -0.08
     yak
    -0.08
     Hoy
    -0.08
     twin
    -0.08
     represented
    -0.08
     legitimately
    -0.08
     Beverage
    -0.08
     finally
    -0.08
     proverb
    -0.08
    POSITIVE LOGITS
     afar
    0.11
    ?v
    0.11
     downwards
    0.11
    lest
    0.11
     IDD
    0.10
    adata
    0.10
     attent
    0.10
     pari
    0.10
    æĺ¯åIJ¦
    0.10
     Attention
    0.10
    Activations Density 0.042%

    No Known Activations