© 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. 30134
    Prev
    Next
    INDEX
    Explanations

    access, discover, witness

    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
    ea
    -0.10
     selling
    -0.10
     sell
    -0.10
    aton
    -0.10
     identifiable
    -0.10
    aim
    -0.10
    bens
    -0.10
     sacr
    -0.10
     lim
    -0.09
    selling
    -0.09
    POSITIVE LOGITS
     access
    0.18
     witnessing
    0.17
     witness
    0.15
     accesses
    0.15
     uncover
    0.15
     priv
    0.14
     firsthand
    0.14
     receive
    0.13
     accessing
    0.13
     discover
    0.13
    Activations Density 0.003%

    No Known Activations