© 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. 113654
    Prev
    Next
    INDEX
    Explanations

    will, would, gonna, ’ll

    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
    sten
    -0.13
    akte
    -0.12
     cooperate
    -0.11
     Holden
    -0.11
     Seek
    -0.11
    aten
    -0.11
    ulan
    -0.10
     ãĤ³
    -0.10
     costing
    -0.10
    ssue
    -0.10
    POSITIVE LOGITS
     encounter
    0.17
     receive
    0.16
     need
    0.16
     hear
    0.16
     see
    0.15
     get
    0.14
     find
    0.14
     be
    0.14
     lose
    0.14
     regret
    0.13
    Activations Density 0.063%

    No Known Activations