© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 163294
    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
    碾
    -0.28
     Hast
    -0.27
    .um
    -0.27
    桶
    -0.26
    声
    -0.26
    edException
    -0.25
    è¾Ī
    -0.25
    éĶ¤
    -0.24
    æĬ¥
    -0.24
     Ensemble
    -0.24
    POSITIVE LOGITS
     Ded
    0.26
    storybook
    0.26
    urrenc
    0.25
     MouseButton
    0.24
    _optional
    0.24
     wholly
    0.23
    è¿Ļåħ¶ä¸Ń
    0.23
    éĢĤçĶ¨
    0.23
     yourselves
    0.23
    åĬ¼
    0.23
    Activations Density 0.010%

    No Known Activations

    This feature has no known activations.