© 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. 88104
    Prev
    Next
    INDEX
    Explanations

    there is/are/was

    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
     Rooney
    -0.10
    uh
    -0.10
     folks
    -0.10
     adequ
    -0.10
    Tube
    -0.10
     arrang
    -0.09
    heck
    -0.09
     asses
    -0.09
    tube
    -0.09
    ược
    -0.09
    POSITIVE LOGITS
     must
    0.10
    bra
    0.09
     needless
    0.08
    å§ĭ
    0.08
    gran
    0.08
     many
    0.08
    å¿ħ
    0.08
    aad
    0.08
     Spo
    0.08
    cest
    0.08
    Activations Density 0.018%

    No Known Activations