© 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. 29864
    Prev
    Next
    INDEX
    Explanations

    phrases ending in 'alysis' or 'asis'

    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
    liness
    -0.13
    yard
    -0.11
    setter
    -0.11
    eller
    -0.10
    eding
    -0.10
    ball
    -0.10
    bler
    -0.10
    ellers
    -0.09
    bell
    -0.09
    anni
    -0.09
    POSITIVE LOGITS
    ipp
    0.09
     tube
    0.09
    /trans
    0.09
     duct
    0.08
     buffered
    0.08
    /ph
    0.08
     Tube
    0.08
    owed
    0.08
    Stra
    0.08
    Nib
    0.08
    Activations Density 0.004%

    No Known Activations