© 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. 46370
    Prev
    Next
    INDEX
    Explanations

    but followed by a clause

    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
     zwar
    -0.14
    quoi
    -0.13
     które
    -0.10
    ÑĬ
    -0.10
    ENO
    -0.10
     że
    -0.10
    lık
    -0.10
    ITOR
    -0.09
    aji
    -0.09
    itals
    -0.09
    POSITIVE LOGITS
    /or
    0.08
    sar
    0.08
    /o
    0.08
    ler
    0.08
    ts
    0.08
    s
    0.08
    illi
    0.08
    arak
    0.08
    onga
    0.07
    lor
    0.07
    Activations Density 0.149%

    No Known Activations