© 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. 26181
    Prev
    Next
    INDEX
    Explanations

    moved or relocated

    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
     clutch
    -0.09
    hed
    -0.09
     urgently
    -0.09
    inch
    -0.09
     Artem
    -0.09
    boss
    -0.08
     bosses
    -0.08
     praying
    -0.08
    855
    -0.08
     interfer
    -0.08
    POSITIVE LOGITS
     moved
    0.22
     relocated
    0.20
     migrated
    0.19
     Moved
    0.18
    moved
    0.17
    Moved
    0.17
     reloc
    0.17
     relocate
    0.16
     relocation
    0.16
     move
    0.15
    Activations Density 0.398%

    No Known Activations