© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5424
    Prev
    Next
    INDEX
    Explanations

    become a/an

    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
    atte
    -0.12
    dia
    -0.11
     ello
    -0.10
     vh
    -0.10
     fathers
    -0.10
    uml
    -0.10
    rne
    -0.10
     detr
    -0.09
    zet
    -0.09
     différentes
    -0.09
    POSITIVE LOGITS
     an
    0.19
     a
    0.18
     part
    0.17
     someone
    0.16
    ä¸Ģ个
    0.14
     employed
    0.14
     member
    0.13
    someone
    0.12
     somebody
    0.12
    -employed
    0.12
    Activations Density 0.345%

    No Known Activations