© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-4B
    3. 19-TRANSCODER-HP
    4. 5784
    Prev
    Next
    INDEX
    Explanations

    File extensions

    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
     detached
    -0.28
    endir
    -0.25
     konk
    -0.25
    橹
    -0.24
    ç¬ij
    -0.24
    ä¼ļå±ķ
    -0.24
    swire
    -0.23
     Buccane
    -0.23
    æĮĩ导æĦıè§ģ
    -0.23
    entials
    -0.23
    POSITIVE LOGITS
    _MAXIMUM
    0.26
    exec
    0.26
    maximum
    0.25
    éĻĢ
    0.25
    source
    0.25
    çªij
    0.24
     ë§Į
    0.24
    ç¹ĩ
    0.24
     Dich
    0.24
    **
    0.24
    Activations Density 0.917%

    No Known Activations