© 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
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5987
    Prev
    Next
    INDEX
    Explanations

    Code related snippets

    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
    ÑĤÑĮ
    -0.28
    å¢
    -0.28
     setting
    -0.28
     Destination
    -0.25
    acket
    -0.24
    inner
    -0.24
    ä¸ĩåIJį
    -0.23
    åłķ
    -0.23
    _destination
    -0.23
    çĽ¸å¹²
    -0.23
    POSITIVE LOGITS
    æĺĻ
    0.31
    ipe
    0.28
    æī¶
    0.28
    ibur
    0.27
    æ¸
    0.26
    ä¸Ģç±»
    0.25
    ipes
    0.25
    spoken
    0.24
    unger
    0.24
    urrenc
    0.24
    Activations Density 0.011%

    No Known Activations