© 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. 15012
    Prev
    Next
    INDEX
    Explanations

    sharing characteristics or responsibilities with

    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
    elf
    -0.14
     Smy
    -0.11
    IGO
    -0.10
     Specialty
    -0.09
    avar
    -0.09
     Trim
    -0.09
     clad
    -0.09
    aval
    -0.09
    elo
    -0.09
     Rand
    -0.09
    POSITIVE LOGITS
     with
    0.21
     avec
    0.16
    	with
    0.16
    with
    0.16
    avec
    0.13
     alongside
    0.13
     dengan
    0.13
     between
    0.11
    partner
    0.11
    ä¸İ
    0.11
    Activations Density 0.187%

    No Known Activations