© 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. 113676
    Prev
    Next
    INDEX
    Explanations

    As [phrase starts]

    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
    ec
    -0.09
     shoe
    -0.08
    247
    -0.08
    ecn
    -0.08
     rein
    -0.08
     Bundy
    -0.08
    115
    -0.08
    lsi
    -0.08
     harness
    -0.08
    æ±Ĥ
    -0.08
    POSITIVE LOGITS
    sembling
    0.16
    cent
    0.15
    ylum
    0.15
    uka
    0.14
    sembled
    0.14
    semble
    0.13
    ymmetric
    0.13
    pects
    0.13
    piring
    0.13
    mode
    0.13
    Activations Density 0.059%

    No Known Activations