© 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. 88544
    Prev
    Next
    INDEX
    Explanations

    moving or changing location

    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
     backstage
    -0.11
     overnight
    -0.10
     Campos
    -0.09
     revolt
    -0.09
     nightly
    -0.09
     cous
    -0.09
     Jail
    -0.09
    uar
    -0.09
     rop
    -0.09
     Mais
    -0.09
    POSITIVE LOGITS
     relocation
    0.51
     reloc
    0.51
     relocated
    0.49
     relocate
    0.48
     moved
    0.46
     moving
    0.45
     move
    0.44
     Moving
    0.43
     Move
    0.40
     movers
    0.40
    Activations Density 0.853%

    No Known Activations