© 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. 30863
    Prev
    Next
    INDEX
    Explanations

    string formatting or data offset

    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
     rivers
    -0.13
    "strings
    -0.11
     Rivers
    -0.11
     nerves
    -0.10
     StringField
    -0.10
     ropes
    -0.10
     wiring
    -0.10
     hoses
    -0.10
     cables
    -0.10
     vines
    -0.10
    POSITIVE LOGITS
     pul
    0.10
     knots
    0.09
    chs
    0.09
     Sho
    0.09
     fillColor
    0.09
     bufsize
    0.08
     Phoenix
    0.08
     Potato
    0.08
    URITY
    0.08
     miracles
    0.08
    Activations Density 0.153%

    No Known Activations