© 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. 89928
    Prev
    Next
    INDEX
    Explanations

    can [verb]

    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
     pouvoir
    -0.14
     poder
    -0.14
     kunnen
    -0.14
     bisa
    -0.14
    åı¯ä»¥
    -0.13
     can
    -0.13
     could
    -0.12
     able
    -0.11
     pute
    -0.11
    èĥ½
    -0.11
    POSITIVE LOGITS
     afford
    0.17
     easily
    0.16
    ’t
    0.16
    /be
    0.15
    /find
    0.14
    /do
    0.14
    't
    0.14
     safely
    0.14
    /control
    0.14
    berra
    0.13
    Activations Density 0.322%

    No Known Activations