© 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. 50063
    Prev
    Next
    INDEX
    Explanations

    deciphering readable text

    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
    327
    -0.11
    andles
    -0.10
    zhou
    -0.10
     Wolff
    -0.10
     stared
    -0.10
    /styles
    -0.09
     multiline
    -0.09
    è½
    -0.09
     stealth
    -0.09
    -scroll
    -0.09
    POSITIVE LOGITS
     decipher
    0.23
     words
    0.22
     intellig
    0.20
     understandable
    0.20
     recognizable
    0.18
     coherent
    0.16
     meanings
    0.16
     readable
    0.16
     discern
    0.15
     meaning
    0.15
    Activations Density 0.190%

    No Known Activations