© 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. 32452
    Prev
    Next
    INDEX
    Explanations

    forming words with consonant clusters and suffixes

    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
     Wich
    -0.10
     claiming
    -0.10
     extras
    -0.10
     intimate
    -0.10
     someone
    -0.09
     hurting
    -0.09
     beaten
    -0.09
     flown
    -0.08
     whilst
    -0.08
     rumored
    -0.08
    POSITIVE LOGITS
     felt
    0.15
     hes
    0.15
     glance
    0.14
     vaguely
    0.13
     regret
    0.13
     nerv
    0.13
     inward
    0.13
     wondered
    0.13
     instinct
    0.12
     glanced
    0.12
    Activations Density 0.007%

    No Known Activations