© 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. 47994
    Prev
    Next
    INDEX
    Explanations

    not / wasn't followed by adjective/noun phrase

    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
    .defaults
    -0.10
     Moy
    -0.10
     Tam
    -0.09
     Cul
    -0.09
    iq
    -0.09
    itch
    -0.09
     tam
    -0.09
    986
    -0.08
    -&
    -0.08
     incor
    -0.08
    POSITIVE LOGITS
     uncommon
    0.15
     unheard
    0.14
     until
    0.14
     surprising
    0.13
     unusual
    0.13
     surprise
    0.12
     fair
    0.11
     everyday
    0.10
     every
    0.10
     Tobias
    0.10
    Activations Density 0.055%

    No Known Activations