© 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. 15540
    Prev
    Next
    INDEX
    Explanations

    like followed by comparison

    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
    uch
    -0.09
    ibble
    -0.09
     did
    -0.08
    ÑģÑĭ
    -0.08
     whole
    -0.08
    aber
    -0.08
    510
    -0.08
     yet
    -0.08
    heimer
    -0.08
    zy
    -0.08
    POSITIVE LOGITS
    WISE
    0.13
    -wise
    0.13
     wise
    0.13
     myself
    0.12
     most
    0.12
     clock
    0.11
     Estr
    0.10
     elsewhere
    0.10
     idiot
    0.10
     many
    0.10
    Activations Density 0.040%

    No Known Activations