© 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. 34073
    Prev
    Next
    INDEX
    Explanations

    hint or toward indications

    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
    Negative Logits
    arth
    -0.10
    edom
    -0.09
    498
    -0.09
     unjust
    -0.09
     instantly
    -0.09
     concentrate
    -0.08
     instinct
    -0.08
    ué
    -0.08
    ARTH
    -0.08
    hour
    -0.08
    POSITIVE LOGITS
     hint
    0.19
     toward
    0.19
     towards
    0.18
     hints
    0.16
     Towards
    0.14
     hinted
    0.14
     Tow
    0.14
     Hint
    0.13
     strongly
    0.12
    Towards
    0.12
    Activations Density 0.019%

    No Known Activations