© 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. 16949
    Prev
    Next
    INDEX
    Explanations

    Harvey Weinstein or parcel delivery

    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
    ated
    -0.11
    -0.10
    ates
    -0.10
    xon
    -0.09
    ating
    -0.09
    istically
    -0.09
    ATED
    -0.08
    quel
    -0.08
    athan
    -0.08
    aceutical
    -0.08
    POSITIVE LOGITS
    iard
    0.12
    aat
    0.11
    echa
    0.11
    rees
    0.11
    ments
    0.11
    ãĥ¡ãĥ³ãĥĪ
    0.11
     slap
    0.11
    alist
    0.10
    ez
    0.10
    icients
    0.10
    Activations Density 0.201%

    No Known Activations