© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 32745
    Prev
    Next
    INDEX
    Explanations

    no words or speaking

    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
    imo
    -0.11
    foy
    -0.10
    Sensitive
    -0.10
     implying
    -0.09
    ieber
    -0.09
    themes
    -0.09
    trak
    -0.09
    "But
    -0.09
     Harr
    -0.09
     pret
    -0.09
    POSITIVE LOGITS
     speak
    0.45
     spoken
    0.42
     spoke
    0.42
     speaks
    0.38
     speaking
    0.38
     Speak
    0.37
     speech
    0.34
     verbal
    0.33
     verbally
    0.30
    Speak
    0.29
    Activations Density 0.113%

    No Known Activations