© 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. 15739
    Prev
    Next
    INDEX
    Explanations

    home and words following

    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
    pector
    -0.08
    mgr
    -0.08
     Gould
    -0.07
    Buzz
    -0.07
     unp
    -0.07
    oria
    -0.07
    arith
    -0.07
    edor
    -0.07
     Repeat
    -0.07
     repeat
    -0.07
    POSITIVE LOGITS
     home
    0.25
    /home
    0.22
    /Home
    0.22
    (home
    0.21
     Home
    0.21
    -home
    0.21
    Home
    0.21
    home
    0.20
     HOME
    0.20
    grown
    0.19
    Activations Density 0.046%

    No Known Activations