© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 117284
    Prev
    Next
    INDEX
    Explanations

    movement into or onto spaces

    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
    izz
    -0.10
    rons
    -0.09
     toughness
    -0.09
    enza
    -0.09
    Arm
    -0.09
     Ferr
    -0.08
     Pos
    -0.08
    fine
    -0.08
    sess
    -0.08
    Mart
    -0.08
    POSITIVE LOGITS
     onto
    0.14
     atop
    0.12
     backed
    0.11
     Lah
    0.10
     bli
    0.09
     peg
    0.09
     into
    0.09
     ACC
    0.09
     demonstr
    0.09
    ippet
    0.08
    Activations Density 0.002%

    No Known Activations