© 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. 162625
    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
    èĪį
    -0.26
    æ±Ĥå©ļ
    -0.25
    æĥ³åĪ°äºĨ
    -0.25
    stell
    -0.25
     convergence
    -0.25
    主ä¹īæĢĿæĥ³
    -0.24
     lightning
    -0.24
     $(
    -0.24
    çıŃ车
    -0.23
    ä¸įä¼ļæľī
    -0.23
    POSITIVE LOGITS
    Pad
    0.30
    esar
    0.27
    赢家
    0.26
    lesi
    0.26
    неÑĨ
    0.25
    oor
    0.25
    åı¯ä»¥ä½¿
    0.24
     Nic
    0.24
    estro
    0.23
    æĶ«
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.