© 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. 7174
    Prev
    Next
    INDEX
    Explanations

    purposes and common methods

    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
    isy
    -0.10
    Posting
    -0.08
     Suit
    -0.07
     fundamentally
    -0.07
    /mod
    -0.07
     stab
    -0.07
     affair
    -0.07
     specially
    -0.07
     priced
    -0.07
     Matters
    -0.07
    POSITIVE LOGITS
     meaning
    0.15
     aim
    0.14
     goal
    0.14
     reason
    0.13
     purpose
    0.13
     implication
    0.13
     preval
    0.13
     premise
    0.13
     extent
    0.12
     intent
    0.12
    Activations Density 0.498%

    No Known Activations