© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 162090
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sho
    -0.26
    hof
    -0.25
    insk
    -0.24
    天åłĤ
    -0.24
    id
    -0.24
    yp
    -0.23
    大æ°Ķ
    -0.23
    æłĩå¿ĹæĢ§
    -0.23
    akers
    -0.23
     newInstance
    -0.23
    POSITIVE LOGITS
    ıldı
    0.26
    istics
    0.25
    æķĻä½ł
    0.25
    è¿ĻäºĽä¸ľè¥¿
    0.25
    )<<
    0.25
    dle
    0.24
    æŃ»äºĨ
    0.24
    (nullptr
    0.24
    è®°å¾Ĺ
    0.24
    dling
    0.23
    Activations Density 0.033%

    No Known Activations

    This feature has no known activations.