© 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. 25970
    Prev
    Next
    INDEX
    Explanations

    iv, Shiv, Kiv, Tiv

    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
    irus
    -0.09
    adio
    -0.09
     emb
    -0.09
    ena
    -0.09
    quest
    -0.09
    alia
    -0.09
    ocked
    -0.09
    icus
    -0.08
    cion
    -0.08
     Zeit
    -0.08
    POSITIVE LOGITS
    ERSION
    0.13
    ELY
    0.10
    ERO
    0.10
     Lucky
    0.10
    оваÑĢ
    0.10
    EST
    0.09
    ernet
    0.09
    opts
    0.09
     Relevant
    0.09
     Trainer
    0.09
    Activations Density 0.052%

    No Known Activations