© 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. 49040
    Prev
    Next
    INDEX
    Explanations

    level shifting, LevelDB, Indicator, deep, BK

    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
    fulness
    -0.13
    apel
    -0.12
    nev
    -0.12
    apple
    -0.11
    amus
    -0.10
    e
    -0.10
    apus
    -0.10
    imals
    -0.10
    itm
    -0.10
    yen
    -0.10
    POSITIVE LOGITS
    led
    0.26
    åĪ«
    0.17
    =logging
    0.15
    .SEVERE
    0.13
    -headed
    0.12
    headed
    0.11
    èģĶ
    0.11
    lement
    0.10
    lops
    0.10
    ocking
    0.10
    Activations Density 0.080%

    No Known Activations