© 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. 5473
    Prev
    Next
    INDEX
    Explanations

    related to knowing something

    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
     wre
    -0.11
     necessity
    -0.09
    uco
    -0.09
     Unsure
    -0.09
     Sens
    -0.09
    untu
    -0.08
     unsure
    -0.08
    OLE
    -0.08
     Fiber
    -0.08
     Spr
    -0.08
    POSITIVE LOGITS
     know
    0.27
     knowing
    0.24
    know
    0.23
     Know
    0.23
    çŁ¥
    0.22
    Know
    0.21
    -know
    0.21
     knows
    0.20
     note
    0.19
     aware
    0.18
    Activations Density 0.100%

    No Known Activations