© 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. 5732
    Prev
    Next
    INDEX
    Explanations

    last resort, recourse, revert

    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
    enci
    -0.10
     è¾ĵ
    -0.09
    astes
    -0.09
    ASTE
    -0.09
    ija
    -0.09
     situ
    -0.09
    levator
    -0.09
     Teddy
    -0.09
     massa
    -0.09
    bris
    -0.09
    POSITIVE LOGITS
     skirts
    0.09
     privilege
    0.09
     Ward
    0.09
    <|fim_suffix|>
    0.09
     everywhere
    0.08
     Downing
    0.08
    Sk
    0.08
    che
    0.08
     Sk
    0.08
    sie
    0.08
    Activations Density 0.001%

    No Known Activations