© 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. 7767
    Prev
    Next
    INDEX
    Explanations

    Code and technical documents

    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
     variable
    -0.25
    é¹ŀ
    -0.25
     illusions
    -0.25
    继
    -0.24
    åĨ¤
    -0.24
    çĹ¹
    -0.24
    chor
    -0.24
    ARIABLE
    -0.24
    variable
    -0.24
    è°¶
    -0.24
    POSITIVE LOGITS
    iesen
    0.27
    mith
    0.27
    <tbody
    0.26
    stin
    0.26
    ijn
    0.26
    addin
    0.26
    pag
    0.26
    èģĶç³»æĸ¹å¼ı
    0.24
    inspace
    0.24
    ensi
    0.24
    Activations Density 0.002%

    No Known Activations