© 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. 3798
    Prev
    Next
    INDEX
    Explanations

    versus/vs

    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
     Sands
    -0.08
    itto
    -0.08
     intermediate
    -0.08
    flo
    -0.07
     obvious
    -0.07
     rud
    -0.06
    iven
    -0.06
     shading
    -0.06
     unofficial
    -0.06
     hei
    -0.06
    POSITIVE LOGITS
     merely
    0.15
     mere
    0.14
    /as
    0.13
    iste
    0.12
     неÑĤ
    0.12
    /=
    0.11
     fingerprints
    0.10
    acles
    0.10
    mere
    0.10
    /from
    0.10
    Activations Density 0.995%

    No Known Activations