© 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. 114952
    Prev
    Next
    INDEX
    Explanations

    2-chloro, 2-deoxy, i/th

    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
     Polly
    -0.09
    eft
    -0.09
    avin
    -0.09
     Marr
    -0.09
    rd
    -0.08
    -quarters
    -0.08
    ivel
    -0.08
     ceilings
    -0.08
    chan
    -0.08
     incompet
    -0.08
    POSITIVE LOGITS
    nd
    0.27
    -thirds
    0.16
     nd
    0.16
    /th
    0.15
    ND
    0.14
     thirds
    0.14
    nds
    0.13
    nde
    0.12
     thumbs
    0.11
     halves
    0.11
    Activations Density 1.324%

    No Known Activations