© 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. 5645
    Prev
    Next
    INDEX
    Explanations

    any ... given

    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
    -or
    -0.10
    lek
    -0.09
     disg
    -0.09
    ÙĬØ©
    -0.08
    aving
    -0.08
    .sax
    -0.08
     ornaments
    -0.08
    avers
    -0.08
    -and
    -0.08
     Subscriber
    -0.08
    POSITIVE LOGITS
     given
    0.19
     GIVEN
    0.17
     case
    0.14
    given
    0.14
     Given
    0.14
    Given
    0.12
    case
    0.11
    _given
    0.11
    dice
    0.11
     point
    0.11
    Activations Density 0.016%

    No Known Activations