© 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. 17866
    Prev
    Next
    INDEX
    Explanations

    preventing or allowing

    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
    angu
    -0.11
     Lose
    -0.10
     undergo
    -0.10
    665
    -0.10
     bag
    -0.10
     lose
    -0.10
     assemble
    -0.10
     pursue
    -0.10
     suffers
    -0.09
     Purs
    -0.09
    POSITIVE LOGITS
    使
    0.20
     prevent
    0.20
     preventing
    0.18
    prevent
    0.17
     allowing
    0.16
     allow
    0.16
     enable
    0.15
     enabling
    0.15
    allow
    0.15
     Prevent
    0.15
    Activations Density 0.426%

    No Known Activations