© 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. 163099
    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
    å¤ĩ
    -0.28
    举æĬ¥çĶµè¯Ŀ
    -0.28
    é¢Ŀ
    -0.25
    erdem
    -0.24
    })();
    -0.24
     strongest
    -0.24
    pecified
    -0.23
    memberof
    -0.23
    igest
    -0.23
    个乡éķĩ
    -0.23
    POSITIVE LOGITS
     gén
    0.29
    typing
    0.29
     gonna
    0.28
    ocus
    0.27
    IENT
    0.27
    ä¾ĽéľĢ
    0.26
    æĻĥ
    0.25
    hua
    0.25
    Aff
    0.25
     typing
    0.24
    Activations Density 0.079%

    No Known Activations

    This feature has no known activations.