© 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. 49344
    Prev
    Next
    INDEX
    Explanations

    whatever, daniel, whatever you love

    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
     behold
    -0.10
     basically
    -0.10
    IRM
    -0.10
    uni
    -0.10
    akra
    -0.10
    ,},↵
    -0.09
     mots
    -0.09
    _banner
    -0.09
     ALWAYS
    -0.09
    éra
    -0.09
    POSITIVE LOGITS
     ain
    0.11
    pis
    0.09
     Mim
    0.09
    UDO
    0.09
     lurking
    0.09
    adoo
    0.08
     Whatever
    0.08
    aniel
    0.08
    quoi
    0.08
    imag
    0.08
    Activations Density 0.017%

    No Known Activations