© 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. 89279
    Prev
    Next
    INDEX
    Explanations

    keys and locks

    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
    oui
    -0.13
    éľ
    -0.10
    ury
    -0.10
     Deutsch
    -0.09
     compartment
    -0.09
     Muss
    -0.09
     muss
    -0.09
     dood
    -0.09
    Plugin
    -0.08
     Lips
    -0.08
    POSITIVE LOGITS
     keys
    0.27
     Keys
    0.26
     Key
    0.24
     key
    0.22
    keys
    0.21
     keyed
    0.21
    Keys
    0.20
    Key
    0.20
     unlocked
    0.20
    -key
    0.19
    Activations Density 0.150%

    No Known Activations