© 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. 28032
    Prev
    Next
    INDEX
    Explanations

    emoticons and positive exclamations

    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
     bullshit
    -0.12
     shitty
    -0.11
     fucking
    -0.11
     Fucking
    -0.11
     FUCK
    -0.11
    fuck
    -0.11
     asshole
    -0.10
     fuck
    -0.10
    Fuck
    -0.10
     fucked
    -0.10
    POSITIVE LOGITS
     :
    0.16
     LOL
    0.15
     :-
    0.15
     lol
    0.15
     XD
    0.15
     ;-
    0.15
     :)
    0.14
     :)↵
    0.14
     ;)
    0.14
     :-)
    0.14
    Activations Density 0.158%

    No Known Activations