© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48656
    Prev
    Next
    INDEX
    Explanations

    licensed, granted, permission, free

    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
     Tut
    -0.11
    olutely
    -0.08
    vely
    -0.08
     Lob
    -0.08
     Kot
    -0.08
    lob
    -0.08
     lob
    -0.08
     Jad
    -0.07
    ly
    -0.07
    amil
    -0.07
    POSITIVE LOGITS
    ward
    0.10
    icana
    0.10
    (es
    0.10
     Duffy
    0.10
    .oc
    0.10
     cad
    0.10
    ales
    0.10
     Alleg
    0.09
    'al
    0.09
    меÑĢ
    0.09
    Activations Density 0.301%

    No Known Activations