© 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. 27634
    Prev
    Next
    INDEX
    Explanations

    known as, training, look at, things you, cycles utilize

    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
     "
    -0.11
     ("
    -0.10
    oba
    -0.10
    —"
    -0.09
    éľĢ
    -0.09
     thru
    -0.09
     cautiously
    -0.09
    [email
    -0.09
     pls
    -0.08
     Dept
    -0.08
    POSITIVE LOGITS
     entirety
    0.13
     incredibly
    0.11
    Overall
    0.10
     alright
    0.10
     oft
    0.10
     massively
    0.10
    .Of
    0.10
     things
    0.10
     Mov
    0.10
    etur
    0.10
    Activations Density 0.611%

    No Known Activations