© 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. 112269
    Prev
    Next
    INDEX
    Explanations

    second derivative

    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
     fours
    -0.11
     four
    -0.09
     Fourth
    -0.09
     fourth
    -0.09
    4
    -0.09
     fifth
    -0.09
     backstage
    -0.08
     perd
    -0.08
     Fifth
    -0.08
    5
    -0.08
    POSITIVE LOGITS
    2
    0.16
    ï¼Ĵ
    0.15
    02
    0.15
     zwe
    0.14
    âĤĤ
    0.14
    -II
    0.14
    ²
    0.13
    ек
    0.13
     II
    0.12
     Second
    0.12
    Activations Density 0.063%

    No Known Activations