© 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. 7866
    Prev
    Next
    INDEX
    Explanations

    dates and possessives

    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
     dodge
    -0.13
    gnore
    -0.11
    specs
    -0.11
    ipay
    -0.11
    mlin
    -0.11
    msp
    -0.11
    OTP
    -0.10
     Merr
    -0.10
    (return
    -0.10
     extrad
    -0.10
    POSITIVE LOGITS
    ï¿
    0.09
    aura
    0.08
    wide
    0.08
    ghi
    0.08
    alo
    0.08
     Mens
    0.08
     stacked
    0.07
    q
    0.07
    ohn
    0.07
    alt
    0.07
    Activations Density 0.188%

    No Known Activations