© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 50711
    Prev
    Next
    INDEX
    Explanations

    fingers, probing, exploring

    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
     walls
    -0.11
     Mam
    -0.09
     internals
    -0.09
     nipples
    -0.09
     kunt
    -0.09
     internal
    -0.09
     Holden
    -0.09
     Rig
    -0.09
     pav
    -0.08
    walls
    -0.08
    POSITIVE LOGITS
     fingertips
    0.14
     fing
    0.14
     probe
    0.13
     probing
    0.12
     probes
    0.12
     misc
    0.12
     grop
    0.12
     fingers
    0.12
    probe
    0.11
     explor
    0.11
    Activations Density 0.019%

    No Known Activations