© 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. 161809
    Prev
    Next
    INDEX
    Explanations

    Banned/Punishment

    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
    ble
    -0.28
    ented
    -0.28
    regn
    -0.27
    .generated
    -0.27
    ores
    -0.27
    asca
    -0.27
    ENTE
    -0.27
     Wars
    -0.27
    ROLS
    -0.27
    izon
    -0.26
    POSITIVE LOGITS
    æĥ©ç½ļ
    0.39
    ä¼ļ被
    0.39
    å¤Ħç½ļ
    0.38
    ç½ļ款
    0.37
    åī¥å¤º
    0.35
     punished
    0.32
    被
    0.32
    è¯Ľ
    0.32
    没æĶ¶
    0.31
    æ¶īå«Į
    0.31
    Activations Density 0.023%

    No Known Activations