© 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. 28505
    Prev
    Next
    INDEX
    Explanations

    required to

    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
     learnt
    -0.14
     equipments
    -0.13
     erst
    -0.12
    lek
    -0.12
     Dit
    -0.12
     [=
    -0.11
     upto
    -0.11
     realise
    -0.11
     organisers
    -0.11
    edere
    -0.11
    POSITIVE LOGITS
     indul
    0.13
     ske
    0.09
     outweigh
    0.09
     promin
    0.08
     preca
    0.08
     indulge
    0.08
     recip
    0.07
     Andr
    0.07
     thumb
    0.07
     stepping
    0.07
    Activations Density 0.281%

    No Known Activations