© 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. 6531
    Prev
    Next
    INDEX
    Explanations

    line numbers

    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
    _STS
    -0.09
    !!)↵
    -0.09
    <|fim_middle|>
    -0.08
     Zap
    -0.08
     adults
    -0.08
    ",-
    -0.08
    /problems
    -0.08
    _TYPED
    -0.08
     those
    -0.08
     Kirst
    -0.08
    POSITIVE LOGITS
    61
    0.09
    39
    0.09
    âĢİ
    0.08
    163
    0.08
    62
    0.08
    54
    0.08
    59
    0.08
    /cal
    0.08
    31
    0.08
    (props
    0.08
    Activations Density 1.427%

    No Known Activations