© 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. 4649
    Prev
    Next
    INDEX
    Explanations

    GUI elements

    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
     whe
    -0.08
     mutual
    -0.07
     sound
    -0.07
     trunk
    -0.07
    VT
    -0.07
     tears
    -0.07
     drip
    -0.07
     voice
    -0.07
     stagger
    -0.07
     screams
    -0.07
    POSITIVE LOGITS
     thumb
    0.15
    -thumb
    0.13
    thumb
    0.12
     fingertips
    0.12
     singled
    0.12
     apex
    0.12
     flick
    0.11
     seasoned
    0.11
     Clips
    0.11
     pinch
    0.11
    Activations Density 0.012%

    No Known Activations