© 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. 28626
    Prev
    Next
    INDEX
    Explanations

    Zone.js or geographical zones

    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
    loo
    -0.13
     Fucked
    -0.12
    orer
    -0.12
    ensen
    -0.12
    dat
    -0.11
    dir
    -0.11
    room
    -0.11
    ivism
    -0.11
    ness
    -0.11
    hoot
    -0.11
    POSITIVE LOGITS
    åŁ
    0.10
    ular
    0.09
    åĪ«
    0.08
    igans
    0.08
    igli
    0.08
    gli
    0.07
    gran
    0.07
    ULAR
    0.07
     Aure
    0.07
    asa
    0.07
    Activations Density 0.026%

    No Known Activations