© 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. 115344
    Prev
    Next
    INDEX
    Explanations

    license version

    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
     âĢİ
    -0.09
     —
    -0.09
     ,
    -0.08
    -0.07
    urga
    -0.07
    âĢij
    -0.07
     PSA
    -0.07
     Isis
    -0.07
     irr
    -0.07
     ENT
    -0.06
    POSITIVE LOGITS
     preg
    0.14
     viagra
    0.13
     allied
    0.13
     cialis
    0.12
    gings
    0.12
    nell
    0.11
    cep
    0.11
    /order
    0.11
    ?s
    0.11
    aghetti
    0.11
    Activations Density 0.009%

    No Known Activations