© 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. 33283
    Prev
    Next
    INDEX
    Explanations

    with location descriptors

    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
     intervening
    -0.10
     riv
    -0.09
     stag
    -0.09
     resp
    -0.08
    atus
    -0.08
    ovel
    -0.08
     Bru
    -0.08
    271
    -0.08
    avors
    -0.08
    utt
    -0.08
    POSITIVE LOGITS
     surrounded
    0.26
     with
    0.21
    with
    0.19
     WITH
    0.17
     amongst
    0.17
     avec
    0.15
     facing
    0.15
    "With
    0.15
    	with
    0.15
     amidst
    0.15
    Activations Density 0.290%

    No Known Activations