© 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. 47936
    Prev
    Next
    INDEX
    Explanations

    inward/outward direction

    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
     intoler
    -0.11
     conditioned
    -0.10
    izon
    -0.09
     proverb
    -0.09
     invariant
    -0.09
    adden
    -0.09
    imat
    -0.09
    ROUT
    -0.09
    conj
    -0.08
     NotFound
    -0.08
    POSITIVE LOGITS
    /out
    0.15
    ness
    0.14
    -facing
    0.13
    -bound
    0.12
     inward
    0.12
    -directed
    0.12
     outward
    0.10
    =out
    0.10
    ly
    0.10
    /Internal
    0.10
    Activations Density 0.013%

    No Known Activations