© 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. 112767
    Prev
    Next
    INDEX
    Explanations

    special characters, punctuation, and 'as example'

    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
     initials
    -0.08
    ipo
    -0.08
     lif
    -0.08
    ŀæĢ§
    -0.08
     neo
    -0.08
     mots
    -0.08
     rip
    -0.08
     vintage
    -0.08
     descriptors
    -0.08
    YG
    -0.08
    POSITIVE LOGITS
     Aluminium
    0.11
    olle
    0.11
     Celsius
    0.11
    venue
    0.10
     Aluminum
    0.10
    adder
    0.10
     receipt
    0.10
     thru
    0.10
    elin
    0.10
     enquiry
    0.10
    Activations Density 0.487%

    No Known Activations