© 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. 162807
    Prev
    Next
    INDEX
    Explanations

    computers and internet

    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
     inf
    -0.30
    furt
    -0.30
     Inf
    -0.28
    inf
    -0.28
     Sung
    -0.26
    Inf
    -0.26
    _inf
    -0.26
    .Inf
    -0.26
    è¦ģæĬĬ
    -0.25
    uzzle
    -0.24
    POSITIVE LOGITS
    åı£æ°´
    0.29
    æ¿Ģèµ·
    0.26
    ä¸Ģçŀ¬éĹ´
    0.26
    笼罩
    0.25
    manship
    0.25
     sleeper
    0.25
    æłı
    0.24
    壳
    0.24
    大巴
    0.24
    enie
    0.24
    Activations Density 0.008%

    No Known Activations