© 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. 29333
    Prev
    Next
    INDEX
    Explanations

    stem cell, interpreter services, restaurant list

    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
     vite
    -0.09
    -cross
    -0.09
    ite
    -0.08
    lags
    -0.08
    _guest
    -0.08
     kla
    -0.08
    ilio
    -0.08
    quick
    -0.07
    abil
    -0.07
    iances
    -0.07
    POSITIVE LOGITS
    swith
    0.17
    sto
    0.16
    sWith
    0.15
    sthrough
    0.14
    stype
    0.13
    ss
    0.12
    stime
    0.12
     finder
    0.12
    spath
    0.12
    ëĵ¤
    0.12
    Activations Density 0.087%

    No Known Activations