© 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. 33576
    Prev
    Next
    INDEX
    Explanations

    direction or movement after a word

    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
     impart
    -0.11
     interrog
    -0.10
     Ung
    -0.08
     apprec
    -0.08
     stepping
    -0.08
     dreaming
    -0.08
     choked
    -0.08
     Sel
    -0.07
     scour
    -0.07
     scav
    -0.07
    POSITIVE LOGITS
    caf
    0.13
     sturdy
    0.12
     zig
    0.12
     makeshift
    0.11
     downwards
    0.11
    -append
    0.11
    neath
    0.11
    cee
    0.11
     whichever
    0.11
     accordingly
    0.11
    Activations Density 0.114%

    No Known Activations