© 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. 92288
    Prev
    Next
    INDEX
    Explanations

    across the street

    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
    oogle
    -0.11
     Forward
    -0.10
     Schwe
    -0.10
    yles
    -0.10
    reme
    -0.09
     clos
    -0.09
    argent
    -0.09
    reg
    -0.09
     Imm
    -0.09
    zones
    -0.09
    POSITIVE LOGITS
     opposite
    0.16
     diagonal
    0.11
     facing
    0.10
     street
    0.10
     opposing
    0.10
    nore
    0.09
     diagon
    0.09
     rav
    0.09
     oppose
    0.09
     Bust
    0.09
    Activations Density 0.017%

    No Known Activations