© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113258
    Prev
    Next
    INDEX
    Explanations

    have to / have a / have any

    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
    ellas
    -0.09
     Kop
    -0.08
     Ready
    -0.08
     supposedly
    -0.08
    972
    -0.08
     Zah
    -0.07
    anova
    -0.07
    zp
    -0.07
    Sept
    -0.07
     threatening
    -0.07
    POSITIVE LOGITS
     Obl
    0.15
     misunderstood
    0.13
     obligation
    0.13
    usher
    0.12
     entitlement
    0.12
     obligations
    0.12
     droit
    0.11
    esseract
    0.11
     rights
    0.11
     derecho
    0.11
    Activations Density 0.059%

    No Known Activations