© 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. 161611
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     But
    -0.32
    еÑģÑĤÑĮ
    -0.28
    èĢĮåľ¨
    -0.28
    ä½Ĩçİ°åľ¨
    -0.27
    ,but
    -0.27
    olute
    -0.26
    èĢĮçİ°åľ¨
    -0.26
    _but
    -0.25
     but
    -0.24
    endid
    -0.24
    POSITIVE LOGITS
    æľīæŶ
    0.27
    å®ĥçļĦ
    0.26
     vÃŃtima
    0.26
    .UTC
    0.25
    åı¯ä»¥è¯´
    0.25
    åĪĻ
    0.25
    .required
    0.25
     its
    0.24
    å°±æĺ¯ä¸Ģ个
    0.24
     required
    0.24
    Activations Density 0.006%

    No Known Activations