© 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. 48168
    Prev
    Next
    INDEX
    Explanations

    screaming, screws, cream, proteo

    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
    ref
    -0.08
    oplast
    -0.08
    izar
    -0.08
    icits
    -0.08
    led
    -0.08
    recursive
    -0.08
    ths
    -0.08
     underst
    -0.07
    Mods
    -0.07
    eb
    -0.07
    POSITIVE LOGITS
    aming
    0.15
     screwed
    0.13
     Screw
    0.12
    naz
    0.12
     Scre
    0.11
     loose
    0.11
    ams
    0.11
     screws
    0.11
     Shots
    0.11
     scre
    0.10
    Activations Density 0.007%

    No Known Activations