© 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. 30775
    Prev
    Next
    INDEX
    Explanations

    may refer to

    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
     idiot
    -0.10
     poorly
    -0.09
     shitty
    -0.09
     nonetheless
    -0.09
     actually
    -0.08
     stupid
    -0.08
     stupidity
    -0.08
     horrible
    -0.08
    arc
    -0.08
     worthless
    -0.08
    POSITIVE LOGITS
     tempting
    0.18
     initially
    0.17
     tempted
    0.14
     flashy
    0.13
     nomin
    0.13
     traditionally
    0.12
     Initially
    0.12
     intimidating
    0.12
     fleeting
    0.12
    tempt
    0.12
    Activations Density 0.049%

    No Known Activations