© 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. 19-TRANSCODER-HP
    7. 5194
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocate
    -0.28
    oscopic
    -0.27
    moid
    -0.27
    çĪ·
    -0.27
     Monter
    -0.27
    OTES
    -0.26
    ĭè¯ķ
    -0.26
    佬
    -0.26
    çĭ®
    -0.25
     Lindsay
    -0.24
    POSITIVE LOGITS
    æºĸ
    0.28
    èĬ±èįī
    0.28
    _precision
    0.27
     forme
    0.25
    亲
    0.25
    管çIJĨåĴĮ
    0.24
    _FORE
    0.24
    ye
    0.24
     hữu
    0.24
    ece
    0.24
    Activations Density 0.198%

    No Known Activations

    This feature has no known activations.