© 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. 17137
    Prev
    Next
    INDEX
    Explanations

    suchsuchSUCHSuchSuchsuchechosenTHESE

    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
    olle
    -0.07
     Pos
    -0.07
    hil
    -0.07
    shi
    -0.07
    kal
    -0.07
     ave
    -0.07
     couple
    -0.07
     Bee
    -0.07
    some
    -0.07
     reasons
    -0.07
    POSITIVE LOGITS
     such
    0.20
    such
    0.17
     SUCH
    0.14
     Such
    0.13
    Such
    0.12
     suche
    0.12
     ÑĤак
    0.12
     chosen
    0.11
     these
    0.11
     THESE
    0.11
    Activations Density 0.032%

    No Known Activations