© 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. 31069
    Prev
    Next
    INDEX
    Explanations

    -minute, -rounded, -paced

    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
     crappy
    -0.13
     admittedly
    -0.11
     ironically
    -0.11
    (and
    -0.11
    (or
    -0.10
    -ish
    -0.10
     crap
    -0.09
     appropriately
    -0.09
     ~~
    -0.09
    dba
    -0.09
    POSITIVE LOGITS
    е
    0.12
    -paced
    0.11
     https
    0.11
     pact
    0.10
    -rounded
    0.10
    https
    0.10
    -minute
    0.10
    fait
    0.10
    /frontend
    0.10
     thrilling
    0.09
    Activations Density 0.029%

    No Known Activations