© 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. 6294
    Prev
    Next
    INDEX
    Explanations

    both things compared

    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
    ablo
    -0.10
    rame
    -0.09
     Venture
    -0.08
    lesson
    -0.08
     balcony
    -0.08
     Hurricane
    -0.08
    RS
    -0.08
     viol
    -0.08
    Jam
    -0.07
    WS
    -0.07
    POSITIVE LOGITS
     alike
    0.14
     similarities
    0.12
     equally
    0.11
     Prostit
    0.11
    rtl
    0.11
     Lub
    0.11
    -Regular
    0.10
    NST
    0.10
     eb
    0.10
     symp
    0.10
    Activations Density 0.002%

    No Known Activations