© 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. 47595
    Prev
    Next
    INDEX
    Explanations

    titles and media content

    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
     simplex
    -0.09
     newbie
    -0.09
     cheap
    -0.08
     seperate
    -0.08
     theoretically
    -0.08
     Overse
    -0.07
    ategorized
    -0.07
     Nordic
    -0.07
    iable
    -0.07
     amis
    -0.07
    POSITIVE LOGITS
     lyrics
    0.19
     Lyrics
    0.16
     song
    0.16
     episode
    0.16
     lyric
    0.15
     soundtrack
    0.14
     Episode
    0.14
     review
    0.14
     meaning
    0.14
     trailer
    0.13
    Activations Density 0.014%

    No Known Activations