© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6100
    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
    è¿ķ
    -0.27
    rier
    -0.27
    ervers
    -0.26
     Valent
    -0.25
    ä¸įåIJĮçļĦ
    -0.25
    stamp
    -0.24
    è¿¥
    -0.24
     commissions
    -0.24
    å¤Ħå¤Ħ
    -0.24
    iom
    -0.24
    POSITIVE LOGITS
     Pepper
    0.31
     pap
    0.28
    å±Ĥ
    0.25
    front
    0.24
    åĺĮ
    0.24
     IMPLEMENT
    0.24
     windshield
    0.23
    rega
    0.23
    _palette
    0.23
    sWith
    0.23
    Activations Density 0.064%

    No Known Activations

    This feature has no known activations.