© 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. 48152
    Prev
    Next
    INDEX
    Explanations

    fourth, 4, CR notations

    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
     zwe
    -0.10
    finity
    -0.09
     Third
    -0.09
    ĥ
    -0.09
    chied
    -0.09
    ?,?,?,?,
    -0.09
    983
    -0.08
    -thirds
    -0.08
    tickets
    -0.08
     Friedman
    -0.08
    POSITIVE LOGITS
     fourth
    0.54
     Fourth
    0.46
    4
    0.43
    ï¼Ķ
    0.37
    Fourth
    0.36
     FOUR
    0.36
     four
    0.35
     forth
    0.35
    -four
    0.35
     fours
    0.34
    Activations Density 0.240%

    No Known Activations