© 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. 14411
    Prev
    Next
    INDEX
    Explanations

    claims, condition, known, meant

    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
    âĢŀ
    -0.10
     occasionally
    -0.09
     vibes
    -0.09
     Hel
    -0.08
     minim
    -0.08
    jest
    -0.08
    OUCH
    -0.08
     —
    -0.08
     maxim
    -0.08
     Maxim
    -0.08
    POSITIVE LOGITS
     Ou
    0.11
    :".$
    0.11
    iry
    0.11
    noinspection
    0.10
     tamb
    0.10
    tered
    0.10
    ente
    0.10
    éĩ
    0.10
     Pew
    0.10
     resetting
    0.10
    Activations Density 0.022%

    No Known Activations