© 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. 8808
    Prev
    Next
    INDEX
    Explanations

    Computer code

    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
    ixe
    -0.28
    åħ¶ä»ĸ
    -0.27
    hte
    -0.27
    åħ¶å®ĥ
    -0.26
     entail
    -0.26
    æŁIJç§į
    -0.25
    åĪ«çļĦ
    -0.25
     flames
    -0.25
    纤维
    -0.24
    hort
    -0.24
    POSITIVE LOGITS
    çIJĨ解åĴĮ
    0.28
    Successfully
    0.28
    æijĨåľ¨
    0.26
    Attempting
    0.25
    ogg
    0.24
     IonicModule
    0.24
    mani
    0.24
    NK
    0.23
    å¾Ĺå¤ļ
    0.23
    å±ķ示äºĨ
    0.23
    Activations Density 0.001%

    No Known Activations