© 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. 6990
    Prev
    Next
    INDEX
    Explanations

    presumably assumes

    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
     crim
    -0.10
     Nah
    -0.10
     competency
    -0.10
    noch
    -0.09
    ahir
    -0.09
     hare
    -0.09
    -&
    -0.09
     nah
    -0.09
    /I
    -0.09
     Warn
    -0.09
    POSITIVE LOGITS
     presumably
    0.49
     presumed
    0.38
     presum
    0.33
    pres
    0.32
     presume
    0.31
     assumed
    0.30
     assum
    0.28
     likely
    0.28
     Pres
    0.28
     Likely
    0.24
    Activations Density 0.393%

    No Known Activations