© 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. 5955
    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
     promot
    -0.26
     hers
    -0.25
     abuse
    -0.25
     ability
    -0.24
    åĨħ
    -0.24
     Laur
    -0.24
     pudd
    -0.24
     ná»Ļi
    -0.23
     Ivy
    -0.23
    TYPO
    -0.23
    POSITIVE LOGITS
    iation
    0.30
    ä¸ºçĽ®æłĩ
    0.29
    USTER
    0.25
    éĢĤåIJĪ
    0.24
    ucker
    0.24
    iations
    0.24
    游
    0.24
    contre
    0.23
    ustin
    0.23
    éĢĤçĶ¨äºİ
    0.23
    Activations Density 3.505%

    No Known Activations

    This feature has no known activations.