© 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. 112048
    Prev
    Next
    INDEX
    Explanations

    a specific type

    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
     differently
    -0.12
     depending
    -0.08
    others
    -0.07
     Buchanan
    -0.07
     differing
    -0.07
    tail
    -0.07
    -ranked
    -0.07
    ARB
    -0.07
    tot
    -0.07
     prohib
    -0.07
    POSITIVE LOGITS
     particular
    0.41
     specific
    0.39
     Specific
    0.28
    specific
    0.27
     particul
    0.26
    Specific
    0.26
     PARTICULAR
    0.25
    _specific
    0.23
    pecific
    0.21
     especÃŃf
    0.21
    Activations Density 0.597%

    No Known Activations