© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36142
    Prev
    Next
    INDEX
    Explanations

    partitioning and managing partitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_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
    ðŁı»
    -0.11
    -0.11
    iness
    -0.11
    erness
    -0.10
    岬
    -0.10
    licity
    -0.10
    产åĮº
    -0.09
    еÑģÑģ
    -0.09
    licit
    -0.09
    á»ĩ
    -0.09
    POSITIVE LOGITS
    nement
    0.13
    edList
    0.12
    ned
    0.12
    ning
    0.11
    numer
    0.11
    ierung
    0.10
    å¼ĢæĿ¥
    0.10
    naire
    0.10
    åĮĸçļĦ
    0.10
    lam
    0.10
    Activations Density 0.042%

    No Known Activations