© 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. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 57267
    Prev
    Next
    INDEX
    Explanations

    temporal adverbs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    QRST
    -0.32
    åıĹåĪ°
    -0.32
    stral
    -0.29
    使æĪij
    -0.27
    ä½ĵçİ°åĩº
    -0.27
     vale
    -0.26
    mapped
    -0.24
    ä¸Ŀ
    -0.24
    ãĤĮãģ¾ãģĻ
    -0.24
    headed
    -0.24
    POSITIVE LOGITS
     finally
    0.42
     eventually
    0.37
     decided
    0.36
    åĨ³å®ļ
    0.32
     ultimately
    0.32
    決å®ļ
    0.31
     recently
    0.31
     reportedly
    0.30
     shut
    0.30
     somehow
    0.30
    Activations Density 0.006%

    No Known Activations