© 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. 25612
    Prev
    Next
    INDEX
    Explanations

    su + following tokens

    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
    ksam
    -0.09
    iele
    -0.09
    shal
    -0.09
     Mend
    -0.09
    egas
    -0.09
    notated
    -0.08
    enticated
    -0.08
    ument
    -0.08
    ustry
    -0.08
    istrator
    -0.08
    POSITIVE LOGITS
    ave
    0.12
    icide
    0.12
    avity
    0.11
     suit
    0.10
    asive
    0.10
     Sweat
    0.10
    ffect
    0.10
     vis
    0.10
    nder
    0.10
     dung
    0.10
    Activations Density 0.007%

    No Known Activations