© 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. 47851
    Prev
    Next
    INDEX
    Explanations

    Wait, allow, let

    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
    alfa
    -0.09
     Vi
    -0.08
     Prefix
    -0.08
    uda
    -0.08
     perpetual
    -0.08
    justify
    -0.07
     disposition
    -0.07
    AFE
    -0.07
     justify
    -0.07
     Entrance
    -0.07
    POSITIVE LOGITS
     allow
    0.37
     Allow
    0.35
     letting
    0.35
     allowing
    0.34
    Allow
    0.33
    allow
    0.31
     allowed
    0.30
     let
    0.29
     wait
    0.29
     waited
    0.29
    Activations Density 0.110%

    No Known Activations