© 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. 32923
    Prev
    Next
    INDEX
    Explanations

    with or possessing

    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
     prem
    -0.08
    because
    -0.08
    kon
    -0.08
     ÑĩÑĤобÑĭ
    -0.08
    onth
    -0.08
    (conv
    -0.07
    pers
    -0.07
     ceremon
    -0.07
    aye
    -0.07
    ?v
    -0.07
    POSITIVE LOGITS
     with
    0.29
    with
    0.23
     possessing
    0.20
     avec
    0.19
    	with
    0.19
     surrounded
    0.18
     accompanied
    0.18
     WITH
    0.17
    ä¸
    0.17
     dengan
    0.17
    Activations Density 0.805%

    No Known Activations