© 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. 18059
    Prev
    Next
    INDEX
    Explanations

    names of bands or fictional characters

    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
     steam
    -0.07
    aptic
    -0.07
    aturing
    -0.07
    oving
    -0.07
    ledged
    -0.07
    atorial
    -0.06
    istically
    -0.06
    ISING
    -0.06
     UIL
    -0.06
    ating
    -0.06
    POSITIVE LOGITS
    engeance
    0.12
    anything
    0.11
     âĻ
    0.11
     Wrong
    0.11
    bucks
    0.11
    archy
    0.11
     busted
    0.10
    romise
    0.10
     Opportunity
    0.10
     necessities
    0.10
    Activations Density 0.522%

    No Known Activations