© 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. 113389
    Prev
    Next
    INDEX
    Explanations

    norm followed by ative

    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
    izable
    -0.11
    ized
    -0.10
    iza
    -0.09
    IZE
    -0.09
    izer
    -0.09
    ness
    -0.09
    ization
    -0.09
    nees
    -0.09
    NESS
    -0.08
    IZER
    -0.08
    POSITIVE LOGITS
    ative
    0.17
    andy
    0.17
    atively
    0.15
    ativity
    0.14
    ally
    0.13
    алÑĮ
    0.13
    ington
    0.12
    als
    0.12
    alth
    0.12
    oxic
    0.12
    Activations Density 0.016%

    No Known Activations