© 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. 33220
    Prev
    Next
    INDEX
    Explanations

    role, function, purpose

    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
     seper
    -0.14
     seperate
    -0.12
     antioxid
    -0.12
     incontr
    -0.11
     initiated
    -0.10
     Portug
    -0.10
     qualche
    -0.10
     alcuni
    -0.10
     deficient
    -0.10
     thats
    -0.09
    POSITIVE LOGITS
     tras
    0.26
    ù
    0.25
    ò
    0.24
    ì
    0.23
    itÃł
    0.22
     possibile
    0.22
     italian
    0.21
    è
    0.21
     bacheca
    0.20
     preval
    0.20
    Activations Density 2.376%

    No Known Activations