© 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. 91657
    Prev
    Next
    INDEX
    Explanations

    symbolic meaning and associations

    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
     unheard
    -0.13
     regrets
    -0.11
     Inquiry
    -0.11
    lav
    -0.11
     erratic
    -0.11
     tolerance
    -0.10
     diligently
    -0.10
     tolerant
    -0.10
     Respons
    -0.10
     disastr
    -0.10
    POSITIVE LOGITS
     symbolism
    0.35
     symbolic
    0.30
     symbol
    0.27
     Symbol
    0.24
    symbol
    0.24
    -symbol
    0.23
    Symbol
    0.22
     symbols
    0.21
     associations
    0.20
     SYMBOL
    0.19
    Activations Density 0.078%

    No Known Activations