© 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. 113559
    Prev
    Next
    INDEX
    Explanations

    technical fields and processes

    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
    (s
    -0.14
    (es
    -0.11
    们
    -0.11
     Dul
    -0.11
    /by
    -0.11
     ceremon
    -0.11
    xes
    -0.11
    ëĵ¤
    -0.10
    /function
    -0.10
    itas
    -0.10
    POSITIVE LOGITS
     techniques
    0.17
     schemes
    0.15
     methods
    0.14
     practices
    0.14
     practiced
    0.14
     done
    0.13
     involving
    0.13
     performed
    0.12
     systems
    0.12
     via
    0.12
    Activations Density 1.625%

    No Known Activations