© 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. 5981
    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
    maint
    -0.27
    awning
    -0.27
    å®ī
    -0.27
    举é£İ
    -0.26
    åı¦
    -0.26
    åIJ¹
    -0.26
    缸åIJĮ
    -0.25
    belief
    -0.25
    för
    -0.24
     Maint
    -0.24
    POSITIVE LOGITS
    nect
    0.28
    ä¸įæĢķ
    0.26
    Digest
    0.25
     Ñģамо
    0.25
    ilies
    0.25
    ual
    0.25
    æıIJ示
    0.24
    _STRUCTURE
    0.24
    å¢ŀéķ¿çİĩ
    0.24
     marty
    0.24
    Activations Density 0.022%

    No Known Activations

    This feature has no known activations.