© 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. 25611
    Prev
    Next
    INDEX
    Explanations

    ack suffix

    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
    ault
    -0.09
    edata
    -0.08
     permanent
    -0.08
    ed
    -0.08
     Permanent
    -0.08
    ality
    -0.07
    436
    -0.07
    eday
    -0.07
     ast
    -0.07
    IME
    -0.07
    POSITIVE LOGITS
    nowled
    0.18
    nowledge
    0.15
    NOWLED
    0.12
    al
    0.11
    e
    0.10
    vect
    0.10
    eous
    0.10
    iel
    0.10
    cept
    0.10
    o
    0.10
    Activations Density 0.002%

    No Known Activations