© 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. 7941
    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
    æ³½
    -0.30
    åįģæĿ¡
    -0.28
    AAF
    -0.28
     textiles
    -0.24
     wp
    -0.24
    CONDITION
    -0.24
    åľ°æĿ¿
    -0.23
    丰
    -0.23
    ulas
    -0.23
    theorem
    -0.23
    POSITIVE LOGITS
    uhn
    0.28
    è¿·
    0.28
     Obl
    0.28
    legg
    0.27
     conjug
    0.26
     bulund
    0.26
     há»ĵi
    0.26
    ForKey
    0.25
     incid
    0.25
    è¤ļ
    0.24
    Activations Density 0.017%

    No Known Activations

    This feature has no known activations.