© 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. 115605
    Prev
    Next
    INDEX
    Explanations

    move [noun]

    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
    acen
    -0.12
    iese
    -0.11
    anel
    -0.11
    istes
    -0.11
    inel
    -0.10
    ammers
    -0.10
    enburg
    -0.10
    rlen
    -0.10
    itters
    -0.09
    radi
    -0.09
    POSITIVE LOGITS
     focus
    0.13
    focus
    0.10
    ansi
    0.10
     attention
    0.10
     glance
    0.09
     hands
    0.09
     attent
    0.09
    ahr
    0.09
     hand
    0.08
    ence
    0.08
    Activations Density 0.009%

    No Known Activations