© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 46787
    Prev
    Next
    INDEX
    Explanations

    following 'to'

    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
    apons
    -0.10
     иÑģполÑĮз
    -0.10
    alla
    -0.08
    958
    -0.08
    uD
    -0.08
     найд
    -0.07
    esson
    -0.07
    ouro
    -0.07
    ','',
    -0.07
    èle
    -0.07
    POSITIVE LOGITS
     to
    0.47
    to
    0.28
    	to
    0.27
     sÄĥ
    0.26
     anz
    0.23
     einz
    0.22
    æĿ¥
    0.21
     бÑĭÑĤÑĮ
    0.19
     ÑĩÑĤобÑĭ
    0.19
    ,to
    0.19
    Activations Density 1.373%

    No Known Activations