© 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. 30152
    Prev
    Next
    INDEX
    Explanations

    prefix indicating something is outside or outward

    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
    bles
    -0.09
    ENCY
    -0.08
    ï¸ı
    -0.08
     salv
    -0.08
    elines
    -0.07
    cing
    -0.07
    isci
    -0.07
    culo
    -0.07
    oins
    -0.07
    acie
    -0.07
    POSITIVE LOGITS
    ekt
    0.15
    ended
    0.14
    uent
    0.13
    usive
    0.13
    empt
    0.13
    ending
    0.13
    iect
    0.13
    licit
    0.13
    usions
    0.13
    ident
    0.12
    Activations Density 0.612%

    No Known Activations