© 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. 47737
    Prev
    Next
    INDEX
    Explanations

    attracted by curiosity, light, or plague

    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
     hunt
    -0.10
     Invitation
    -0.09
    ando
    -0.09
     penetr
    -0.08
     desperation
    -0.08
     Dominic
    -0.08
     eag
    -0.08
     Diaz
    -0.08
     invitation
    -0.08
    zza
    -0.08
    POSITIVE LOGITS
     moth
    0.14
    moth
    0.12
     unavoidable
    0.12
    awai
    0.11
     sworn
    0.11
     inev
    0.11
    ibi
    0.10
     electrom
    0.10
    è®°å½ķ
    0.10
    653
    0.10
    Activations Density 0.002%

    No Known Activations