© 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. 91436
    Prev
    Next
    INDEX
    Explanations

    joint actions and group results

    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
     herself
    -0.33
     her
    -0.17
     she
    -0.16
    she
    -0.15
     himself
    -0.12
     his
    -0.11
    She
    -0.11
     She
    -0.10
    /is
    -0.10
    å¥
    -0.10
    POSITIVE LOGITS
     jointly
    0.35
     collectively
    0.34
     yourselves
    0.30
     themselves
    0.28
     together
    0.24
     unanimously
    0.23
     joint
    0.23
     collective
    0.21
    joint
    0.21
     united
    0.20
    Activations Density 0.001%

    No Known Activations