© 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. 5990
    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
     Plan
    -0.28
    Plan
    -0.27
    igu
    -0.26
     comedian
    -0.25
    _plan
    -0.25
    ä¸įåĪ©
    -0.25
     celebrity
    -0.24
    津贴
    -0.24
    $__
    -0.24
    __$
    -0.24
    POSITIVE LOGITS
     sap
    0.28
    soft
    0.27
     lat
    0.27
    å¯Ħ
    0.26
     Svens
    0.25
    åĪļ
    0.24
    æļĸ
    0.24
    åľ°ä¸Ĭ
    0.24
    æľīæŶ
    0.24
     оÑĢг
    0.24
    Activations Density 0.231%

    No Known Activations

    This feature has no known activations.