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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 8123
    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
    èĩªç§°
    -0.27
     skulls
    -0.26
     link
    -0.25
     Link
    -0.24
    åıªæĢķ
    -0.24
    Maker
    -0.24
    ç¬Ħ
    -0.23
     postpone
    -0.23
    åĬ³åĬ¨
    -0.23
     onwards
    -0.23
    POSITIVE LOGITS
    oad
    0.28
    éĺ¿å¯Į
    0.26
    ary
    0.26
    __.__
    0.26
    à¸Ĺร
    0.25
    iche
    0.24
    è¤
    0.24
    otypes
    0.23
     holster
    0.23
    YSIS
    0.23
    Activations Density 0.016%

    No Known Activations

    This feature has no known activations.