© 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. 14405
    Prev
    Next
    INDEX
    Explanations

    ials / ness / ess

    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
    e
    -0.15
    es
    -0.14
    er
    -0.13
     Scaffold
    -0.10
    dea
    -0.10
    thouse
    -0.09
    eus
    -0.09
     stead
    -0.09
    ejs
    -0.08
    ION
    -0.08
    POSITIVE LOGITS
    entially
    0.17
    entials
    0.17
    s
    0.16
    ing
    0.16
    ence
    0.13
    quire
    0.13
    cio
    0.12
    ential
    0.12
    rum
    0.12
    entication
    0.11
    Activations Density 0.025%

    No Known Activations