© 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. 4803
    Prev
    Next
    INDEX
    Explanations

    turn, time, or your turn

    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
    isle
    -0.09
    ics
    -0.09
    castle
    -0.08
     ath
    -0.08
    acier
    -0.08
     accompagn
    -0.08
    ighthouse
    -0.08
     xd
    -0.08
     import
    -0.08
    nat
    -0.08
    POSITIVE LOGITS
     turn
    0.42
     Turn
    0.28
    è½
    0.26
    turn
    0.26
    Turn
    0.25
    -turn
    0.24
     turno
    0.24
    _turn
    0.24
    TURN
    0.22
     turns
    0.22
    Activations Density 0.111%

    No Known Activations