© 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. 31256
    Prev
    Next
    INDEX
    Explanations

    see the

    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
     seeing
    -0.13
    _seen
    -0.11
     Bew
    -0.11
     seen
    -0.11
     hinter
    -0.10
    è¦ĭ
    -0.10
    /script
    -0.10
    è§ģ
    -0.10
    ships
    -0.10
     showroom
    -0.10
    POSITIVE LOGITS
    /he
    0.16
    /read
    0.13
     cref
    0.12
    -through
    0.12
    eing
    0.12
    eee
    0.11
    eeee
    0.10
    ign
    0.10
    /find
    0.10
    /k
    0.10
    Activations Density 0.132%

    No Known Activations