© 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. 90048
    Prev
    Next
    INDEX
    Explanations

    linking verbs followed by adjectives or participles

    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
     Uma
    -0.12
     afore
    -0.12
    _bio
    -0.12
    еÑģÑĮ
    -0.12
     INCLUDED
    -0.11
     perpetr
    -0.11
    /if
    -0.11
     discre
    -0.11
    !,↵
    -0.11
    ersed
    -0.11
    POSITIVE LOGITS
     also
    0.22
     therefore
    0.18
    also
    0.17
     however
    0.15
     then
    0.14
     thus
    0.12
    however
    0.12
    then
    0.10
     Also
    0.10
     even
    0.10
    Activations Density 0.159%

    No Known Activations