© 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. 31062
    Prev
    Next
    INDEX
    Explanations

    journal of

    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
    imap
    -0.10
     Sob
    -0.10
    ORM
    -0.10
    ings
    -0.10
     Kingston
    -0.09
    lus
    -0.09
    orer
    -0.09
     Falk
    -0.09
     Baxter
    -0.09
     manual
    -0.09
    POSITIVE LOGITS
    CPP
    0.09
     attribution
    0.08
     hypocrisy
    0.08
     sponsor
    0.08
     sanct
    0.08
     legit
    0.08
     Deutsch
    0.08
     turkey
    0.08
     Distrib
    0.08
    /dir
    0.08
    Activations Density 0.001%

    No Known Activations