© 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. 6397
    Prev
    Next
    INDEX
    Explanations

    touching or reaching

    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
     devis
    -0.11
     chop
    -0.10
     devised
    -0.10
     privately
    -0.10
     conco
    -0.10
     fore
    -0.10
     scram
    -0.10
     devise
    -0.10
     wanted
    -0.09
    strup
    -0.09
    POSITIVE LOGITS
     touches
    0.16
     touched
    0.15
     touch
    0.15
     touching
    0.15
     reaches
    0.15
     reached
    0.14
     intersect
    0.14
     touchdown
    0.13
     landed
    0.13
     meets
    0.12
    Activations Density 0.043%

    No Known Activations