© 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. 162667
    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
    -sem
    -0.27
    hari
    -0.26
    itech
    -0.26
    (',');↵
    -0.25
    ↵        ↵        ↵
    -0.25
    _ANDROID
    -0.24
    _logits
    -0.24
    lops
    -0.24
    ä¸įæĪIJ
    -0.24
    Colon
    -0.24
    POSITIVE LOGITS
    ç´ł
    0.30
    说æĪij
    0.28
    å¤ľéĩĮ
    0.27
     Middle
    0.26
     middle
    0.26
    aments
    0.26
     programm
    0.25
    éĻĪåĪĹ
    0.25
    Middle
    0.25
     Connect
    0.24
    Activations Density 0.011%

    No Known Activations

    This feature has no known activations.