© 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. 5798
    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
    sut
    -0.32
    atitude
    -0.28
     Seamless
    -0.26
    æĸ§
    -0.26
    åī©
    -0.26
    åıªè§ģ
    -0.24
    ersion
    -0.24
    ä»Ħ
    -0.24
    çIJļ
    -0.24
    æ»ī
    -0.23
    POSITIVE LOGITS
    çĪ±å¥ĩèīº
    0.25
     logical
    0.25
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.25
     di
    0.24
    èŀį
    0.24
     won
    0.23
     innate
    0.23
    ä¸ŃåĽ½åĽ½éĻħ
    0.23
     relative
    0.23
     dziaÅĤania
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.