© 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. 49164
    Prev
    Next
    INDEX
    Explanations

    please followed by a word

    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
    izon
    -0.10
     Hutchinson
    -0.10
    /per
    -0.10
    dens
    -0.10
    OOK
    -0.09
    marsh
    -0.09
    UTO
    -0.09
    iana
    -0.09
     initializer
    -0.09
     charisma
    -0.09
    POSITIVE LOGITS
     fronts
    0.09
    wf
    0.08
    ainter
    0.08
    -on
    0.08
    rk
    0.08
    alf
    0.08
    v
    0.08
    MET
    0.08
     industri
    0.07
    osal
    0.07
    Activations Density 0.118%

    No Known Activations