© 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. 28711
    Prev
    Next
    INDEX
    Explanations

    back into, over, crossing, immediate

    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
    adam
    -0.08
    oso
    -0.08
    pone
    -0.08
     anticipation
    -0.08
     Blues
    -0.08
     sluggish
    -0.08
     stranded
    -0.08
    etur
    -0.08
    oren
    -0.08
     stagnant
    -0.08
    POSITIVE LOGITS
    ewe
    0.11
     Crossing
    0.10
     kay
    0.10
     crossing
    0.10
     threshold
    0.10
     immedi
    0.10
     Generating
    0.09
    andal
    0.09
    ¡
    0.09
     immediate
    0.09
    Activations Density 0.002%

    No Known Activations