© 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. 18305
    Prev
    Next
    INDEX
    Explanations

    famous men and their surnames

    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
    keeper
    -0.07
    lies
    -0.06
    ctl
    -0.06
     Jacqueline
    -0.06
    edith
    -0.06
    ees
    -0.06
    omap
    -0.06
    George
    -0.06
    gra
    -0.06
    ble
    -0.05
    POSITIVE LOGITS
     fucking
    0.20
     Fucking
    0.18
     freaking
    0.16
     bloody
    0.14
     Freak
    0.13
     freak
    0.13
     FUCK
    0.12
     Guinness
    0.12
     Picasso
    0.12
    ->__
    0.12
    Activations Density 0.425%

    No Known Activations