© 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. 161790
    Prev
    Next
    INDEX
    Explanations

    advice

    np_max-act · gemini-2.0-flash
    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
    å°±è¦ģ
    -0.26
    ¥¿
    -0.26
    edom
    -0.25
    ä¸Ģç±»
    -0.25
    rray
    -0.25
    tone
    -0.25
     Tone
    -0.24
    idi
    -0.24
    idos
    -0.23
    rases
    -0.23
    POSITIVE LOGITS
    Compact
    0.29
     Compact
    0.26
     afterwards
    0.26
     vs
    0.25
    sut
    0.23
     babys
    0.23
     Amendments
    0.23
    輪
    0.23
     later
    0.23
    çĽijäºĭ
    0.23
    Activations Density 0.029%

    No Known Activations