© 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. 8280
    Prev
    Next
    INDEX
    Explanations

    build

    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
     examiner
    -0.26
    avian
    -0.25
    eworthy
    -0.25
    å¹²èѦ
    -0.25
    felt
    -0.24
     simult
    -0.24
    .uniform
    -0.23
    åĺĽ
    -0.23
    çļĦäºĭ
    -0.23
    larımız
    -0.23
    POSITIVE LOGITS
    ä½ĨçĶ±äºİ
    0.28
    é©·
    0.28
    èĢĮåľ¨
    0.27
    è¾ĥä½İ
    0.25
    (lo
    0.25
     Lob
    0.25
     volum
    0.25
    罩
    0.24
    itle
    0.24
    åĪ«
    0.24
    Activations Density 0.049%

    No Known Activations