© 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. 113760
    Prev
    Next
    INDEX
    Explanations

    over the years

    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
    &C
    -0.08
     fore
    -0.07
    á»ı
    -0.07
     Wedding
    -0.07
    allas
    -0.07
     embargo
    -0.07
     Ars
    -0.07
    ient
    -0.07
    ear
    -0.07
     sens
    -0.07
    POSITIVE LOGITS
    -span
    0.13
     span
    0.12
    -long
    0.12
     spanning
    0.12
    _until
    0.11
     cul
    0.11
    yst
    0.11
    SPAN
    0.11
     various
    0.11
    pan
    0.11
    Activations Density 0.155%

    No Known Activations