© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 4209
    Prev
    Next
    INDEX
    Explanations

    writing and fun

    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
     Warp
    -0.10
    Cop
    -0.10
     Semi
    -0.09
    Miller
    -0.09
     Cir
    -0.09
     titles
    -0.09
    erez
    -0.09
    titles
    -0.09
     Miller
    -0.09
    vert
    -0.09
    POSITIVE LOGITS
     fun
    0.13
     researching
    0.12
     writing
    0.12
    FUN
    0.12
    fun
    0.11
     FUN
    0.11
    -writing
    0.10
    Writing
    0.10
    writing
    0.10
     Bosch
    0.10
    Activations Density 0.035%

    No Known Activations