© 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. 115142
    Prev
    Next
    INDEX
    Explanations

    interjections and affirmations

    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
    abl
    -0.09
    unlikely
    -0.09
    gend
    -0.09
     neighb
    -0.08
     nat
    -0.08
     exp
    -0.08
    antd
    -0.08
    -Cs
    -0.08
    vari
    -0.08
    VENT
    -0.08
    POSITIVE LOGITS
     huh
    0.31
     truly
    0.24
     indeed
    0.20
     Truly
    0.20
     really
    0.18
     sometimes
    0.17
     eh
    0.17
     evidently
    0.16
     definitely
    0.15
    åķ
    0.15
    Activations Density 0.138%

    No Known Activations