© 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. 115601
    Prev
    Next
    INDEX
    Explanations

    starts with a conjunction or punctuation

    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
     moreover
    -0.11
    cf
    -0.10
    alia
    -0.10
     RUN
    -0.10
     Registro
    -0.10
     Suff
    -0.10
    ва
    -0.09
    Triple
    -0.09
     Doming
    -0.09
     perse
    -0.09
    POSITIVE LOGITS
    Although
    0.13
    While
    0.13
     Although
    0.12
    Whether
    0.12
     While
    0.12
     Whether
    0.11
    Many
    0.11
    Rather
    0.10
    Since
    0.10
     although
    0.10
    Activations Density 0.101%

    No Known Activations