© 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. 115141
    Prev
    Next
    INDEX
    Explanations

    Ta words

    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
    e
    -0.09
    amon
    -0.09
    orp
    -0.09
    horse
    -0.09
    ACTER
    -0.08
    712
    -0.08
     RIP
    -0.08
     aud
    -0.08
    nob
    -0.08
    Delivery
    -0.08
    POSITIVE LOGITS
     Ta
    0.12
    iping
    0.12
    affe
    0.11
     ta
    0.11
    edium
    0.11
     kontakt
    0.11
    -da
    0.11
    VERN
    0.11
    iga
    0.10
    ught
    0.10
    Activations Density 0.012%

    No Known Activations