© 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. 5458
    Prev
    Next
    INDEX
    Explanations

    but followed by verb

    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
     contradict
    -0.13
     contrad
    -0.12
    zn
    -0.12
    ince
    -0.12
    _ce
    -0.12
    way
    -0.11
     vista
    -0.11
    mens
    -0.11
    vez
    -0.10
    uki
    -0.10
    POSITIVE LOGITS
    eton
    0.10
    ame
    0.08
     heir
    0.08
     realistically
    0.07
     financier
    0.07
     Gong
    0.07
    Oi
    0.07
     unquestion
    0.07
     handc
    0.07
     repl
    0.07
    Activations Density 0.001%

    No Known Activations