© 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. 16646
    Prev
    Next
    INDEX
    Explanations

    case, values, floor, round, treatment, state, versions

    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
    usch
    -0.11
    -but
    -0.10
    lash
    -0.10
    ita
    -0.10
    itas
    -0.10
    imm
    -0.10
    dd
    -0.09
    qid
    -0.09
     nors
    -0.09
    roid
    -0.09
    POSITIVE LOGITS
    ;
    0.12
    ayah
    0.10
     mentre
    0.09
     whereas
    0.09
    807
    0.09
    rek
    0.09
     cac
    0.08
     Brushes
    0.08
     Chow
    0.08
     Kinder
    0.08
    Activations Density 1.151%

    No Known Activations