© 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. 32947
    Prev
    Next
    INDEX
    Explanations

    very high/important/new/much/convenient/hard/slow

    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
    udo
    -0.11
     decidedly
    -0.10
     gig
    -0.09
    STS
    -0.09
    iba
    -0.09
    .svg
    -0.09
    irk
    -0.09
     downright
    -0.09
     hin
    -0.09
    aga
    -0.09
    POSITIVE LOGITS
    anyak
    0.09
     defiant
    0.09
    .gc
    0.09
     Assass
    0.08
    aac
    0.08
     notorious
    0.08
    aq
    0.08
     infamous
    0.08
     Prem
    0.08
    lav
    0.08
    Activations Density 0.079%

    No Known Activations