© 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. 6539
    Prev
    Next
    INDEX
    Explanations

    virtual

    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
    ever
    -0.10
    et
    -0.09
    o
    -0.08
    ettes
    -0.08
    feed
    -0.08
    hire
    -0.08
    inh
    -0.07
    ấ
    -0.07
    Tiny
    -0.07
    Postal
    -0.07
    POSITIVE LOGITS
     reality
    0.28
     Reality
    0.25
    Reality
    0.22
     realities
    0.17
    ization
    0.16
     worlds
    0.15
    -real
    0.15
    .Virtual
    0.14
    ity
    0.14
     virtual
    0.13
    Activations Density 0.039%

    No Known Activations