© 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. 29893
    Prev
    Next
    INDEX
    Explanations

    exclusive rights or access

    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
     unexpected
    -0.12
     unavoid
    -0.10
    Unexpected
    -0.10
     diligent
    -0.10
    /window
    -0.10
    /random
    -0.09
     STATIC
    -0.09
     Static
    -0.09
     unfamiliar
    -0.09
    ÙĬÙĦ
    -0.09
    POSITIVE LOGITS
     privileges
    0.20
     privilege
    0.19
     privileged
    0.19
     coveted
    0.16
     Priv
    0.16
     reserved
    0.15
     precious
    0.14
     prestigious
    0.14
     anymore
    0.13
     sacred
    0.13
    Activations Density 0.155%

    No Known Activations