© 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. 9118
    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
    cks
    -0.25
    nings
    -0.25
    ç²
    -0.24
    ãĥ¼ãĥ«
    -0.24
    %(
    -0.24
    bere
    -0.24
     bite
    -0.24
    kim
    -0.24
    izons
    -0.23
    _birth
    -0.23
    POSITIVE LOGITS
     stead
    0.28
    ogr
    0.27
    etry
    0.26
    tet
    0.25
    殿
    0.25
    à¹Ģà¸Ĺศ
    0.25
    å®ŀéĻħè¡ĮåĬ¨
    0.24
    æĥħ
    0.24
    ä¹ĭä½Ļ
    0.24
    ENA
    0.24
    Activations Density 0.210%

    No Known Activations

    This feature has no known activations.