© 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. 17258
    Prev
    Next
    INDEX
    Explanations

    well known or established

    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
     Kings
    -0.09
     mult
    -0.09
     sl
    -0.09
     fill
    -0.08
     Nath
    -0.08
     Fay
    -0.08
     Pred
    -0.08
     convers
    -0.08
     Pra
    -0.08
     attentive
    -0.08
    POSITIVE LOGITS
    -known
    0.21
     known
    0.19
    known
    0.18
     recognized
    0.17
     recognised
    0.16
    -established
    0.16
     Known
    0.15
    recognized
    0.14
     renowned
    0.14
     reputed
    0.14
    Activations Density 0.062%

    No Known Activations