© 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. 32649
    Prev
    Next
    INDEX
    Explanations

    implements, possibility, immun, temporomandibular, insufficient

    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
    nesday
    -0.19
    arently
    -0.19
    PointerException
    -0.18
    rastructure
    -0.18
    aternion
    -0.18
    thern
    -0.17
    iculty
    -0.17
    tesy
    -0.17
    auty
    -0.16
    iams
    -0.16
    POSITIVE LOGITS
    raries
    0.14
    o
    0.10
    i
    0.10
    etheless
    0.10
    pared
    0.10
    vised
    0.09
    aData
    0.09
    amel
    0.09
    en
    0.09
    u
    0.09
    Activations Density 0.615%

    No Known Activations