© 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. 90140
    Prev
    Next
    INDEX
    Explanations

    song titles with durations

    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
     Tennessee
    -0.10
    dings
    -0.10
     Tenn
    -0.10
    imps
    -0.09
     Confirmation
    -0.09
    orne
    -0.09
    ipl
    -0.09
     dall
    -0.09
    esch
    -0.09
     fourteen
    -0.08
    POSITIVE LOGITS
     Blu
    0.10
    Launching
    0.09
     importantly
    0.09
    apat
    0.09
    cash
    0.09
    oca
    0.09
     successor
    0.08
    @if
    0.08
    BV
    0.08
    Wonder
    0.08
    Activations Density 0.002%

    No Known Activations