© 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. 111997
    Prev
    Next
    INDEX
    Explanations

    seventh, 7, VII, seven

    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
     sixteen
    -0.11
    326
    -0.10
     Palmer
    -0.10
    594
    -0.09
     ten
    -0.09
    deaux
    -0.09
     commodity
    -0.09
    256
    -0.09
    riba
    -0.09
    ERM
    -0.09
    POSITIVE LOGITS
     seventh
    0.39
     Seventh
    0.35
    7
    0.33
     VII
    0.32
     seven
    0.30
    -seven
    0.26
     Seven
    0.26
    ï¼Ĺ
    0.25
    07
    0.24
     July
    0.23
    Activations Density 0.161%

    No Known Activations