© 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. 4855
    Prev
    Next
    INDEX
    Explanations

    years old or older

    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
     (>
    -0.09
    ãĢģ
    -0.08
     Fifth
    -0.08
    etc
    -0.07
    olia
    -0.07
     omn
    -0.07
    esser
    -0.07
     Rob
    -0.07
    yc
    -0.07
    ifo
    -0.07
    POSITIVE LOGITS
    +)
    0.13
    +↵↵
    0.12
    enberg
    0.11
    iks
    0.11
    +.
    0.11
    (or
    0.11
    +↵
    0.10
     consenting
    0.10
     minded
    0.10
    )+↵
    0.10
    Activations Density 0.051%

    No Known Activations