© 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. 116588
    Prev
    Next
    INDEX
    Explanations

    talking closely

    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
     theirs
    -0.14
    Their
    -0.13
    their
    -0.13
     their
    -0.12
    ä»ĸ
    -0.11
    they
    -0.11
     THEIR
    -0.11
    They
    -0.11
     him
    -0.11
     Their
    -0.10
    POSITIVE LOGITS
     aup
    0.15
     chez
    0.14
     assisting
    0.12
     courtesy
    0.12
    <typeof
    0.11
     Mr
    0.11
     sund
    0.11
    对
    0.10
    idden
    0.10
    isko
    0.10
    Activations Density 0.774%

    No Known Activations