© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7232
    Prev
    Next
    INDEX
    Explanations

    Recurring events

    np_max-act · gemini-2.0-flash
    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
    åĶ¤
    -0.26
     Fitzgerald
    -0.24
    configure
    -0.24
     tz
    -0.23
    åľ¨ä¸Ģ
    -0.23
    Bre
    -0.23
    à¹Ģà¸ķ
    -0.23
    jni
    -0.23
    IGH
    -0.23
     hij
    -0.23
    POSITIVE LOGITS
    åıijå±ķçIJĨ念
    0.27
    çĪ±ç¾İ
    0.26
     Prev
    0.26
    åīįåIJİ
    0.24
    èĢĮå·²
    0.24
    åĨ¢
    0.24
    /angular
    0.24
    vie
    0.23
    éĻįèIJ½
    0.23
    âĹ»
    0.23
    Activations Density 0.032%

    No Known Activations