© 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. 114336
    Prev
    Next
    INDEX
    Explanations

    user input and submission

    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
     regimes
    -0.10
    ogan
    -0.10
    ogi
    -0.10
     encouraged
    -0.09
    urge
    -0.09
     Hodg
    -0.09
     misguided
    -0.09
     contingent
    -0.08
    reas
    -0.08
     Span
    -0.08
    POSITIVE LOGITS
     entered
    0.23
     submitted
    0.22
     input
    0.21
     inputs
    0.20
    entered
    0.16
     Entered
    0.16
     uploaded
    0.16
     Input
    0.16
    è¾ĵåħ¥
    0.16
     declared
    0.15
    Activations Density 0.674%

    No Known Activations