© 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. 33193
    Prev
    Next
    INDEX
    Explanations

    self-related concepts

    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
    ator
    -0.10
     Lew
    -0.09
    /testing
    -0.09
     tackled
    -0.09
    ometown
    -0.09
    ando
    -0.09
     conj
    -0.08
    /sources
    -0.08
    -short
    -0.08
     coll
    -0.08
    POSITIVE LOGITS
    -aware
    0.15
    lessness
    0.13
    -contained
    0.12
    contained
    0.12
    -expression
    0.12
    ÂŃt
    0.11
    âĢij
    0.11
    -destruct
    0.11
    destruct
    0.10
     contained
    0.10
    Activations Density 0.032%

    No Known Activations