© 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. 114780
    Prev
    Next
    INDEX
    Explanations

    Âł followed by punctuation or dates

    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
    ERO
    -0.08
     Chandler
    -0.08
    
    -0.08
     chic
    -0.08
    Tumblr
    -0.08
     practically
    -0.07
    489
    -0.07
     Hung
    -0.07
    tie
    -0.07
     flown
    -0.07
    POSITIVE LOGITS
    /co
    0.11
     indis
    0.11
    indi
    0.10
    inke
    0.10
    /animate
    0.10
     gent
    0.10
    amel
    0.10
    indle
    0.10
    /render
    0.10
     Tran
    0.09
    Activations Density 0.086%

    No Known Activations