© 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. 31843
    Prev
    Next
    INDEX
    Explanations

    scratch

    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
     crush
    -0.11
     Samar
    -0.10
     Crusher
    -0.09
     dah
    -0.09
     shock
    -0.09
    resh
    -0.09
    jar
    -0.08
     Baghd
    -0.08
    ëªħ
    -0.08
    indr
    -0.08
    POSITIVE LOGITS
     itch
    0.16
    apixel
    0.11
     scratch
    0.10
    SCR
    0.10
     Scratch
    0.10
     Acres
    0.09
     lightly
    0.09
     Claw
    0.09
    (SC
    0.09
    otos
    0.09
    Activations Density 0.025%

    No Known Activations