© 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. 20-TRANSCODER-HP
    7. 63368
    Prev
    Next
    INDEX
    Explanations

    Grammatical context and data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    媳
    -0.29
    hq
    -0.27
    åĥĸ
    -0.26
    ivid
    -0.26
    erver
    -0.26
    èij£äºĭä¼ļ
    -0.25
     verbosity
    -0.25
    å¦ĤæѤ
    -0.25
     verbose
    -0.24
    _types
    -0.24
    POSITIVE LOGITS
    .innerHeight
    0.30
    Axes
    0.25
    xmm
    0.25
     nipples
    0.25
     kaz
    0.25
    ä¸į平衡
    0.25
    uja
    0.24
    Aj
    0.24
    ardin
    0.24
    	placeholder
    0.24
    Activations Density 6.976%

    No Known Activations