© 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. 116916
    Prev
    Next
    INDEX
    Explanations

    local path indicators

    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
     sperm
    -0.10
     fetish
    -0.10
     hak
    -0.10
     intercourse
    -0.09
     porn
    -0.09
     semen
    -0.09
     cleanup
    -0.09
     ejac
    -0.09
     attractiveness
    -0.09
     Splash
    -0.09
    POSITIVE LOGITS
    -Origin
    0.10
     Consolid
    0.10
     consolidated
    0.10
    locs
    0.10
     delivered
    0.10
     RemoteException
    0.10
     deliveries
    0.09
    ë¡Ŀ
    0.09
    icious
    0.09
     loads
    0.09
    Activations Density 0.005%

    No Known Activations