© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31833
    Prev
    Next
    INDEX
    Explanations

    fitting or modifying to

    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
    stro
    -0.11
    hlen
    -0.11
    issant
    -0.11
    acular
    -0.11
     Cair
    -0.10
    ixa
    -0.10
    kv
    -0.10
    PX
    -0.10
    kp
    -0.10
     Pag
    -0.10
    POSITIVE LOGITS
     suit
    0.24
     fit
    0.21
     resemble
    0.17
     suite
    0.16
     match
    0.15
    suit
    0.15
     accommodate
    0.15
     reflect
    0.13
     suits
    0.13
     fits
    0.13
    Activations Density 0.310%

    No Known Activations