© 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. 49092
    Prev
    Next
    INDEX
    Explanations

    conclusion or explanation

    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
     fucked
    -0.16
     shitty
    -0.16
     fucking
    -0.15
     fuck
    -0.15
     shit
    -0.14
     wherein
    -0.13
     Fuck
    -0.13
    Fuck
    -0.13
    fuck
    -0.13
     aforementioned
    -0.12
    POSITIVE LOGITS
     Definitely
    0.13
     luckily
    0.12
     conveniently
    0.11
     definitely
    0.11
     fortunately
    0.11
    fortunately
    0.10
    PLL
    0.10
     unexpectedly
    0.10
     amazingly
    0.10
     plenty
    0.09
    Activations Density 2.629%

    No Known Activations