© 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. 33126
    Prev
    Next
    INDEX
    Explanations

    fun and interesting

    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
     tremend
    -0.11
    Vel
    -0.11
     consect
    -0.11
    ABI
    -0.11
    azer
    -0.10
    agn
    -0.10
     magna
    -0.10
    alon
    -0.10
     vel
    -0.10
    iras
    -0.10
    POSITIVE LOGITS
     interesting
    0.42
     fun
    0.39
    interesting
    0.33
     Interesting
    0.31
     exciting
    0.30
    Interesting
    0.28
     juicy
    0.26
    fun
    0.26
     Fun
    0.25
     interess
    0.22
    Activations Density 0.214%

    No Known Activations