© 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. 7119
    Prev
    Next
    INDEX
    Explanations

    words starting with con

    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
    orage
    -0.08
    ustry
    -0.07
    ür
    -0.07
     Expert
    -0.07
    ource
    -0.07
    onth
    -0.07
    itecture
    -0.07
    ledged
    -0.06
    ocene
    -0.06
    pis
    -0.06
    POSITIVE LOGITS
    olly
    0.15
    fluence
    0.13
    ning
    0.13
    ifers
    0.13
    joined
    0.13
    fection
    0.12
    current
    0.12
    stance
    0.12
    IFA
    0.12
    ifer
    0.12
    Activations Density 0.029%

    No Known Activations