© 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. 5694
    Prev
    Next
    INDEX
    Explanations

    numbers following 'I'

    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
     è¾ĵ
    -0.08
     bowed
    -0.08
     underlying
    -0.08
     infused
    -0.08
     conting
    -0.08
     Asheville
    -0.08
     Giz
    -0.08
     Porno
    -0.08
     scrim
    -0.08
     narrow
    -0.08
    POSITIVE LOGITS
    26
    0.14
    22
    0.14
    29
    0.13
    28
    0.13
    24
    0.13
    19
    0.13
    31
    0.13
    34
    0.13
    23
    0.13
    36
    0.13
    Activations Density 0.751%

    No Known Activations